We have been discussing some simple ideas from statistical learning theory. PR NPTEL course p.1/123

Size: px
Start display at page:

Download "We have been discussing some simple ideas from statistical learning theory. PR NPTEL course p.1/123"

Transcription

1 We have been discussing some simple ideas from statistical learning theory. PR NPTEL course p.1/123

2 We have been discussing some simple ideas from statistical learning theory. The risk minimization framework that we discussed gives us a better perspective on understanding the unifying theme in different learning algorithms. PR NPTEL course p.2/123

3 We have been discussing some simple ideas from statistical learning theory. The risk minimization framework that we discussed gives us a better perspective on understanding the unifying theme in different learning algorithms. We will now go back to studying pattern classification algorithms. PR NPTEL course p.3/123

4 We have been discussing some simple ideas from statistical learning theory. The risk minimization framework that we discussed gives us a better perspective on understanding the unifying theme in different learning algorithms. We will now go back to studying pattern classification algorithms. We will first briefly review algorithms for learning linear classifiers and then start looking at methods to learn nonlinear classifiers. PR NPTEL course p.4/123

5 Linear Models In the two class case, the linear classifier is given by h(x) = sign(w T X + w 0 ) PR NPTEL course p.5/123

6 Linear Models In the two class case, the linear classifier is given by h(x) = sign(w T X + w 0 ) We have seen that we can also think of h(x) as h(x) = sign(w T Φ(X) + w 0 ), where Φ(X) = [φ 1 (X),,φ m (X)] T as long as φ i are fixed (possibly non-linear) functions. PR NPTEL course p.6/123

7 We discussed many algorithms for learning W. PR NPTEL course p.7/123

8 We discussed many algorithms for learning W. The Perceptron algorithm is a simple error-correcting method that is guarenteed to find a separating hyperplane if one exists. PR NPTEL course p.8/123

9 We discussed many algorithms for learning W. The Perceptron algorithm is a simple error-correcting method that is guarenteed to find a separating hyperplane if one exists. The perceptron convergence theorem shows that given any training set of linearly separable patterns, the algorithm will find a separating hyperplane. PR NPTEL course p.9/123

10 We discussed many algorithms for learning W. The Perceptron algorithm is a simple error-correcting method that is guarenteed to find a separating hyperplane if one exists. The perceptron convergence theorem shows that given any training set of linearly separable patterns, the algorithm will find a separating hyperplane. Our discussion on statistical learning theory gives us an idea of how many iid examples we should have before we can be confident that the hyperplane that separates the examples will also do well on test data. PR NPTEL course p.10/123

11 We have also seen the least-squares method where we find W to minimize J(W) = 1 n i (W T X i y i ) 2 where, for simplicity of notation, we have assumed augumented feature vectors. PR NPTEL course p.11/123

12 We have also seen the least-squares method where we find W to minimize J(W) = 1 n i (W T X i y i ) 2 where, for simplicity of notation, we have assumed augumented feature vectors. In our risk minimization framework, H is parametrized by W, we take h(x) = W T X and minimize empirical risk under squared-error loss function. PR NPTEL course p.12/123

13 We have seen how to obtain the least-squares solution: W = (A T A) 1 A T Y where rows of matrix A are feature vectors and components of Y are y i. PR NPTEL course p.13/123

14 We have seen how to obtain the least-squares solution: W = (A T A) 1 A T Y where rows of matrix A are feature vectors and components of Y are y i. The least-squares method can also be used to learn linear regression models. PR NPTEL course p.14/123

15 We have seen how to obtain the least-squares solution: W = (A T A) 1 A T Y where rows of matrix A are feature vectors and components of Y are y i. The least-squares method can also be used to learn linear regression models. The only difference is that in a regression model, the y i are real-valued. PR NPTEL course p.15/123

16 We have seen that we can also minimize the empirical risk J(W) using gradient descent. PR NPTEL course p.16/123

17 We have seen that we can also minimize the empirical risk J(W) using gradient descent. We can also run this gradient descent in an incremental fashion by considering one example at a time. PR NPTEL course p.17/123

18 We have seen that we can also minimize the empirical risk J(W) using gradient descent. We can also run this gradient descent in an incremental fashion by considering one example at a time. That gives us another classical algorithm called the LMS algorithm. PR NPTEL course p.18/123

19 We have also seen that we can use the least squares idea to learn a model g(w T X) by redefining J as J(W) = 1 n i (g(w T X i ) y i ) 2 PR NPTEL course p.19/123

20 We have also seen that we can use the least squares idea to learn a model g(w T X) by redefining J as J(W) = 1 n i (g(w T X i ) y i ) 2 An important example is the logistic regression where we take g as the sigmoid function. PR NPTEL course p.20/123

21 We have also seen that we can use the least squares idea to learn a model g(w T X) by redefining J as J(W) = 1 n i (g(w T X i ) y i ) 2 An important example is the logistic regression where we take g as the sigmoid function. We minimize J by incremental version of gradient descent. PR NPTEL course p.21/123

22 Another important method for learning linear classifiers is the Fisher Linear Discriminant. PR NPTEL course p.22/123

23 Another important method for learning linear classifiers is the Fisher Linear Discriminant. Here, we look for a direction W such that the patterns of the two classes get well-separated when projected onto this one-dimensional subspace. PR NPTEL course p.23/123

24 Another important method for learning linear classifiers is the Fisher Linear Discriminant. Here, we look for a direction W such that the patterns of the two classes get well-separated when projected onto this one-dimensional subspace. As we mentioned, Fisher Linear Discriminant can be thought of as a special case of least-squares method of learning a linear regression model with special target values. PR NPTEL course p.24/123

25 Beyond linear models Learning linear models (classifiers) is generally efficient. PR NPTEL course p.25/123

26 Beyond linear models Learning linear models (classifiers) is generally efficient. However, linear models are not always sufficient. PR NPTEL course p.26/123

27 Beyond linear models Learning linear models (classifiers) is generally efficient. However, linear models are not always sufficient. Best linear functions may still be a poor fit. PR NPTEL course p.27/123

28 Beyond linear models Learning linear models (classifiers) is generally efficient. However, linear models are not always sufficient. Best linear functions may still be a poor fit. We have looked at three broad approaches to learning nonlinear classifiers. PR NPTEL course p.28/123

29 Beyond linear models Learning linear models (classifiers) is generally efficient. However, linear models are not always sufficient. Best linear functions may still be a poor fit. We have looked at three broad approaches to learning nonlinear classifiers. We now discuss neural network models. PR NPTEL course p.29/123

30 Neural network models We need a good parameterized class of nonlinear functions to learn nonlinear classifiers. PR NPTEL course p.30/123

31 Neural network models We need a good parameterized class of nonlinear functions to learn nonlinear classifiers. Artificial neural networks are one such class PR NPTEL course p.31/123

32 Neural network models We need a good parameterized class of nonlinear functions to learn nonlinear classifiers. Artificial neural networks are one such class Nonlinear functions are built up through composition of summation and sigmoids. PR NPTEL course p.32/123

33 Neural network models We need a good parameterized class of nonlinear functions to learn nonlinear classifiers. Artificial neural networks are one such class Nonlinear functions are built up through composition of summation and sigmoids. Useful for both classification and Regression. PR NPTEL course p.33/123

34 In this course we will study only multilayer feedforward networks. PR NPTEL course p.34/123

35 In this course we will study only multilayer feedforward networks. They are useful because they offer good parameterized class of nonlinear functions and there are some efficient algorithms to learn them. PR NPTEL course p.35/123

36 In this course we will study only multilayer feedforward networks. They are useful because they offer good parameterized class of nonlinear functions and there are some efficient algorithms to learn them. However, historically, development of (artificial) neural network models was motivated by some ideas on the structure of human brain. PR NPTEL course p.36/123

37 In this course we will study only multilayer feedforward networks. They are useful because they offer good parameterized class of nonlinear functions and there are some efficient algorithms to learn them. However, historically, development of (artificial) neural network models was motivated by some ideas on the structure of human brain. We briefly look at this perspective of neural networks as an approach to engineering intelligent systems. PR NPTEL course p.37/123

38 What is an Artificial Neural Network? PR NPTEL course p.38/123

39 What is an Artificial Neural Network? "A parallel distributed information processor made up of simple processing units that has a propensity for acquiring problem solving knowledge through experience" PR NPTEL course p.39/123

40 What is an Artificial Neural Network? "A parallel distributed information processor made up of simple processing units that has a propensity for acquiring problem solving knowledge through experience" Large number of inter connected units PR NPTEL course p.40/123

41 What is an Artificial Neural Network? "A parallel distributed information processor made up of simple processing units that has a propensity for acquiring problem solving knowledge through experience" Large number of inter connected units Each unit implements simple function, nonlinear PR NPTEL course p.41/123

42 What is an Artificial Neural Network? "A parallel distributed information processor made up of simple processing units that has a propensity for acquiring problem solving knowledge through experience" Large number of inter connected units Each unit implements simple function, nonlinear The knowledge resides in the interconnection strengths. PR NPTEL course p.42/123

43 What is an Artificial Neural Network? "A parallel distributed information processor made up of simple processing units that has a propensity for acquiring problem solving knowledge through experience" Large number of inter connected units Each unit implements simple function, nonlinear The knowledge resides in the interconnection strengths. Problem solving ability is often through learning PR NPTEL course p.43/123

44 What is an Artificial Neural Network? "A parallel distributed information processor made up of simple processing units that has a propensity for acquiring problem solving knowledge through experience" Large number of inter connected units Each unit implements simple function, nonlinear The knowledge resides in the interconnection strengths. Problem solving ability is often through learning An architecture inspired by the structure of Brain PR NPTEL course p.44/123

45 The Human Brain Neuron - the basic computing unit PR NPTEL course p.45/123

46 The Human Brain Neuron - the basic computing unit Brain is a highly organized structure of networks of interconnected neurons PR NPTEL course p.46/123

47 The Human Brain Neuron - the basic computing unit Brain is a highly organized structure of networks of interconnected neurons In the Brain No of neurons (100 billion) PR NPTEL course p.47/123

48 The Human Brain Neuron - the basic computing unit Brain is a highly organized structure of networks of interconnected neurons In the Brain No of neurons (100 billion) Average synapses per neuron ( ) PR NPTEL course p.48/123

49 The Human Brain Neuron - the basic computing unit Brain is a highly organized structure of networks of interconnected neurons In the Brain No of neurons (100 billion) Average synapses per neuron ( ) Total synapses PR NPTEL course p.49/123

50 The Human Brain Neuron - the basic computing unit Brain is a highly organized structure of networks of interconnected neurons In the Brain No of neurons (100 billion) Average synapses per neuron ( ) Total synapses Neuron time constants Milliseconds PR NPTEL course p.50/123

51 The Human Brain Neuron - the basic computing unit Brain is a highly organized structure of networks of interconnected neurons In the Brain No of neurons (100 billion) Average synapses per neuron ( ) Total synapses Neuron time constants Milliseconds Single neuron can send 100 spikes per second PR NPTEL course p.51/123

52 A rough estimate of processing power: One arithmetic operation per synapse 10 4 operations per neuron per spike 10 6 operations per neuron per sec operations per sec!! (A gigaflop is 10 9 operations, teraflop is operations!) PR NPTEL course p.52/123

53 A rough estimate of processing power: One arithmetic operation per synapse 10 4 operations per neuron per spike 10 6 operations per neuron per sec operations per sec!! (A gigaflop is 10 9 operations, teraflop is operations!) Massive parallelism can deliver massive computing power, PR NPTEL course p.53/123

54 A rough estimate of processing power: One arithmetic operation per synapse 10 4 operations per neuron per spike 10 6 operations per neuron per sec operations per sec!! (A gigaflop is 10 9 operations, teraflop is operations!) Massive parallelism can deliver massive computing power, if we know how to manage it PR NPTEL course p.54/123

55 Digital computers: Precise design, highly constrained, not very adaptive or fault tolerant, Centralized control, deterministic, basic switching times 10 9 sec PR NPTEL course p.55/123

56 Digital computers: Precise design, highly constrained, not very adaptive or fault tolerant, Centralized control, deterministic, basic switching times 10 9 sec Natural neural networks: massively parallel, highly adaptive and fault tolerant, self configuring, self repairing, noisy, stochastic, basic switching time 10 3 sec PR NPTEL course p.56/123

57 Digital computers: Precise design, highly constrained, not very adaptive or fault tolerant, Centralized control, deterministic, basic switching times 10 9 sec Natural neural networks: massively parallel, highly adaptive and fault tolerant, self configuring, self repairing, noisy, stochastic, basic switching time 10 3 sec Most capabilities of Brain are LEARNT. PR NPTEL course p.57/123

58 Artificial Intelligence (AI) Understanding intelligence in computational terms. PR NPTEL course p.58/123

59 Artificial Intelligence (AI) Understanding intelligence in computational terms. Developing machines that are intelligent. PR NPTEL course p.59/123

60 Artificial Intelligence (AI) Understanding intelligence in computational terms. Developing machines that are intelligent. At least two distinct approaches PR NPTEL course p.60/123

61 Artificial Intelligence (AI) Understanding intelligence in computational terms. Developing machines that are intelligent. At least two distinct approaches Try to model intelligent behavior in terms of processing structured symbols. (Resulting methods, algorithms etc may not resemble brain at the implementation level) PR NPTEL course p.61/123

62 Artificial Intelligence (AI) Understanding intelligence in computational terms. Developing machines that are intelligent. At least two distinct approaches Try to model intelligent behavior in terms of processing structured symbols. (Resulting methods, algorithms etc may not resemble brain at the implementation level) A second approach is based on mimicking human brain at architectural/implementation level PR NPTEL course p.62/123

63 The symbolic AI approach Brain is to be understood in computational terms only PR NPTEL course p.63/123

64 The symbolic AI approach Brain is to be understood in computational terms only Physical symbol system hypothesis PR NPTEL course p.64/123

65 The symbolic AI approach Brain is to be understood in computational terms only Physical symbol system hypothesis A digital computer is a universal symbol manipulator and can be programmed to be intelligent PR NPTEL course p.65/123

66 The symbolic AI approach Brain is to be understood in computational terms only Physical symbol system hypothesis A digital computer is a universal symbol manipulator and can be programmed to be intelligent Many useful engineering applications e.g. Expert systems PR NPTEL course p.66/123

67 The symbolic AI approach Brain is to be understood in computational terms only Physical symbol system hypothesis A digital computer is a universal symbol manipulator and can be programmed to be intelligent Many useful engineering applications e.g. Expert systems An implicit faith: The architecture of Brain per se is irrelevant for engineering intelligent artifacts PR NPTEL course p.67/123

68 Artificial Neural Networks Can be viewed as one approach towards understanding brain/building intelligent machines PR NPTEL course p.68/123

69 Artificial Neural Networks Can be viewed as one approach towards understanding brain/building intelligent machines Computational architectures inspired by brain PR NPTEL course p.69/123

70 Artificial Neural Networks Can be viewed as one approach towards understanding brain/building intelligent machines Computational architectures inspired by brain Computational methods for learning dependencies in data stream PR NPTEL course p.70/123

71 Artificial Neural Networks Can be viewed as one approach towards understanding brain/building intelligent machines Computational architectures inspired by brain Computational methods for learning dependencies in data stream e.g. Pattern Recognition, System identification PR NPTEL course p.71/123

72 Artificial Neural Networks Can be viewed as one approach towards understanding brain/building intelligent machines Computational architectures inspired by brain Computational methods for learning dependencies in data stream e.g. Pattern Recognition, System identification Characteristics: Emergent properties, learning, self adaptation PR NPTEL course p.72/123

73 Artificial Neural Networks Can be viewed as one approach towards understanding brain/building intelligent machines Computational architectures inspired by brain Computational methods for learning dependencies in data stream e.g. Pattern Recognition, System identification Characteristics: Emergent properties, learning, self adaptation Modeling Biology? Mathematically purified neurons!! PR NPTEL course p.73/123

74 Artificial Neural Networks Computing machines that try to mimic brain architecture. PR NPTEL course p.74/123

75 Artificial Neural Networks Computing machines that try to mimic brain architecture. A large network of interconnected units PR NPTEL course p.75/123

76 Artificial Neural Networks Computing machines that try to mimic brain architecture. A large network of interconnected units Each unit has simple input-output mapping PR NPTEL course p.76/123

77 Artificial Neural Networks Computing machines that try to mimic brain architecture. A large network of interconnected units Each unit has simple input-output mapping Each interconnection has numerical weight attached to it PR NPTEL course p.77/123

78 Artificial Neural Networks Computing machines that try to mimic brain architecture. A large network of interconnected units Each unit has simple input-output mapping Each interconnection has numerical weight attached to it Output of unit depends on outputs and connection weights of units connected to it PR NPTEL course p.78/123

79 Artificial Neural Networks Computing machines that try to mimic brain architecture. A large network of interconnected units Each unit has simple input-output mapping Each interconnection has numerical weight attached to it Output of unit depends on outputs and connection weights of units connected to it Knowledge resides in the weights PR NPTEL course p.79/123

80 Artificial Neural Networks Computing machines that try to mimic brain architecture. A large network of interconnected units Each unit has simple input-output mapping Each interconnection has numerical weight attached to it Output of unit depends on outputs and connection weights of units connected to it Knowledge resides in the weights Problem solving ability is often through learning PR NPTEL course p.80/123

81 Single neuron model PR NPTEL course p.81/123

82 Single neuron model x i are inputs into the (artificial) neuron and w i are the corresponding weights. y is the output of the neuron PR NPTEL course p.82/123

83 Single neuron model x i are inputs into the (artificial) neuron and w i are the corresponding weights. y is the output of the neuron Net input : η = j w jx j output: y = f(η), where f(.) is called activation function PR NPTEL course p.83/123

84 Single neuron model x i are inputs into the (artificial) neuron and w i are the corresponding weights. y is the output of the neuron Net input : η = j w jx j output: y = f(η), where f(.) is called activation function (Perceptron, AdaLinE are such models). PR NPTEL course p.84/123

85 Networks of neurons We can connect a number of such units or neurons to form a network. Inputs to a neuron can be outputs of other neurons (and/or external inputs). PR NPTEL course p.85/123

86 Networks of neurons We can connect a number of such units or neurons to form a network. Inputs to a neuron can be outputs of other neurons (and/or external inputs). PR NPTEL course p.86/123

87 Networks of neurons We can connect a number of such units or neurons to form a network. Inputs to a neuron can be outputs of other neurons (and/or external inputs). Notation: y j output of j th neuron; w ij weight of connection from neuron i to neuron j. PR NPTEL course p.87/123

88 Each neuron computes weighted sum of inputs and passes it through its activation function, to compute output PR NPTEL course p.88/123

89 Each neuron computes weighted sum of inputs and passes it through its activation function, to compute output For example, output of neuron 5 is y 5 = f 5 (w 35 y 3 + w 45 y 4 ) PR NPTEL course p.89/123

90 Each neuron computes weighted sum of inputs and passes it through its activation function, to compute output For example, output of neuron 5 is y 5 = f 5 (w 35 y 3 + w 45 y 4 ) = f 5 (w 35 f 3 (w 13 y 1 + w 23 y 2 ) + w 45 f 4 (w 14 y 1 + w 24 y 2 )) PR NPTEL course p.90/123

91 Each neuron computes weighted sum of inputs and passes it through its activation function, to compute output For example, output of neuron 5 is y 5 = f 5 (w 35 y 3 + w 45 y 4 ) = f 5 (w 35 f 3 (w 13 y 1 + w 23 y 2 ) + w 45 f 4 (w 14 y 1 + w 24 y 2 )) By convention, we take y 1 = x 1 and y 2 = x 2. PR NPTEL course p.91/123

92 Each neuron computes weighted sum of inputs and passes it through its activation function, to compute output For example, output of neuron 5 is y 5 = f 5 (w 35 y 3 + w 45 y 4 ) = f 5 (w 35 f 3 (w 13 y 1 + w 23 y 2 ) + w 45 f 4 (w 14 y 1 + w 24 y 2 )) By convention, we take y 1 = x 1 and y 2 = x 2. Here, x 1, x 2 are inputs and y 5, y 6 are outputs. PR NPTEL course p.92/123

93 A single neuron represents a class of functions from R m to R. PR NPTEL course p.93/123

94 A single neuron represents a class of functions from R m to R. Specific set of weights realise specific functions. PR NPTEL course p.94/123

95 A single neuron represents a class of functions from R m to R. Specific set of weights realise specific functions. By interconnecting many units/neurons, networks can represent more complicated functions from R m to R m. PR NPTEL course p.95/123

96 A single neuron represents a class of functions from R m to R. Specific set of weights realise specific functions. By interconnecting many units/neurons, networks can represent more complicated functions from R m to R m. The architecture constrains the function class that can be represented. Weights define specific function in the class. PR NPTEL course p.96/123

97 A single neuron represents a class of functions from R m to R. Specific set of weights realise specific functions. By interconnecting many units/neurons, networks can represent more complicated functions from R m to R m. The architecture constrains the function class that can be represented. Weights define specific function in the class. To form meaningful networks, nonlinearity of activation function is important. PR NPTEL course p.97/123

98 Typical activation functions 1. Hard limiter: f(x) = 1 if x > τ = 0 otherwise PR NPTEL course p.98/123

99 Typical activation functions 1. Hard limiter: f(x) = 1 if x > τ = 0 otherwise We can keep the τ to be zero and add one more input line to the neuron. An example of a single neuron with this activation function is Perceptron. PR NPTEL course p.99/123

100 Activation functions (cont) Sigmoid function: f(x) = a 1 + exp ( bx), a, b > 0 PR NPTEL course p.100/123

101 Activation functions (Contd.) 3. tanh f(x) = atanh(bx), a, b > 0 PR NPTEL course p.101/123

102 Why study such models? A belief that the architecture of Brain is critical to intelligent behavior. PR NPTEL course p.102/123

103 Why study such models? A belief that the architecture of Brain is critical to intelligent behavior. Models can implement highly nonlinear functions. They are adaptive and can be trained. PR NPTEL course p.103/123

104 Why study such models? A belief that the architecture of Brain is critical to intelligent behavior. Models can implement highly nonlinear functions. They are adaptive and can be trained. Useful in many applications PR NPTEL course p.104/123

105 Why study such models? A belief that the architecture of Brain is critical to intelligent behavior. Models can implement highly nonlinear functions. They are adaptive and can be trained. Useful in many applications Time series prediction PR NPTEL course p.105/123

106 Why study such models? A belief that the architecture of Brain is critical to intelligent behavior. Models can implement highly nonlinear functions. They are adaptive and can be trained. Useful in many applications Time series prediction system identification and control PR NPTEL course p.106/123

107 Why study such models? A belief that the architecture of Brain is critical to intelligent behavior. Models can implement highly nonlinear functions. They are adaptive and can be trained. Useful in many applications Time series prediction system identification and control pattern recognition and Regression PR NPTEL course p.107/123

108 Why study such models? A belief that the architecture of Brain is critical to intelligent behavior. Models can implement highly nonlinear functions. They are adaptive and can be trained. Useful in many applications Time series prediction system identification and control pattern recognition and Regression Model can help us understand Brain function Computational neuroscience PR NPTEL course p.108/123

109 Many different models are possible PR NPTEL course p.109/123

110 Many different models are possible Evolution: Discrete time / continuous time synchronous / asynchronous deterministic / stochastic PR NPTEL course p.110/123

111 Many different models are possible Evolution: Discrete time / continuous time synchronous / asynchronous deterministic / stochastic Interconnections: Feedforward / having feedback PR NPTEL course p.111/123

112 Many different models are possible Evolution: Discrete time / continuous time synchronous / asynchronous deterministic / stochastic Interconnections: Feedforward / having feedback States or outputs of units: binary / finitely many / continuous PR NPTEL course p.112/123

113 Recurrent networks The network we saw earlier has no feedback. PR NPTEL course p.113/123

114 Recurrent networks The network we saw earlier has no feedback. Here is an example of a network with feedback PR NPTEL course p.114/123

115 Recurrent networks The network we saw earlier has no feedback. Here is an example of a network with feedback Can model a dynamical system: y(k) = f(y(k 1), x 1 (k), x 2 (k)) PR NPTEL course p.115/123

116 We will consider only feedforward networks which provide a general class of nonlinear functions. PR NPTEL course p.116/123

117 We will consider only feedforward networks which provide a general class of nonlinear functions. These can always be organized as a layered network. PR NPTEL course p.117/123

118 We will consider only feedforward networks which provide a general class of nonlinear functions. These can always be organized as a layered network. This network represents a class of functions from R 2 to R 2. PR NPTEL course p.118/123

119 Each unit can also have a bias input. PR NPTEL course p.119/123

120 Each unit can also have a bias input. This is shown for a single unit below. PR NPTEL course p.120/123

121 Each unit can also have a bias input. This is shown for a single unit below. One can always think of bias as an extra input y = f ( d i=1 w i x i + w 0 ) PR NPTEL course p.121/123

122 Each unit can also have a bias input. This is shown for a single unit below. One can always think of bias as an extra input ( d ) ( d y = f w i x i + w 0 = f i=1 i=0 ) w i x i, x 0 = +1 PR NPTEL course p.122/123

123 Multilayer feedforward networks Here is a general multilayer feedforward network. PR NPTEL course p.123/123

Neural Networks and Support Vector Machines

Neural Networks and Support Vector Machines INF5390 - Kunstig intelligens Neural Networks and Support Vector Machines Roar Fjellheim INF5390-13 Neural Networks and SVM 1 Outline Neural networks Perceptrons Neural networks Support vector machines

More information

Artificial Neural Networks and Support Vector Machines. CS 486/686: Introduction to Artificial Intelligence

Artificial Neural Networks and Support Vector Machines. CS 486/686: Introduction to Artificial Intelligence Artificial Neural Networks and Support Vector Machines CS 486/686: Introduction to Artificial Intelligence 1 Outline What is a Neural Network? - Perceptron learners - Multi-layer networks What is a Support

More information

Introduction to Machine Learning and Data Mining. Prof. Dr. Igor Trajkovski trajkovski@nyus.edu.mk

Introduction to Machine Learning and Data Mining. Prof. Dr. Igor Trajkovski trajkovski@nyus.edu.mk Introduction to Machine Learning and Data Mining Prof. Dr. Igor Trakovski trakovski@nyus.edu.mk Neural Networks 2 Neural Networks Analogy to biological neural systems, the most robust learning systems

More information

Machine Learning and Pattern Recognition Logistic Regression

Machine Learning and Pattern Recognition Logistic Regression Machine Learning and Pattern Recognition Logistic Regression Course Lecturer:Amos J Storkey Institute for Adaptive and Neural Computation School of Informatics University of Edinburgh Crichton Street,

More information

Lecture 6. Artificial Neural Networks

Lecture 6. Artificial Neural Networks Lecture 6 Artificial Neural Networks 1 1 Artificial Neural Networks In this note we provide an overview of the key concepts that have led to the emergence of Artificial Neural Networks as a major paradigm

More information

PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 4: LINEAR MODELS FOR CLASSIFICATION

PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 4: LINEAR MODELS FOR CLASSIFICATION PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 4: LINEAR MODELS FOR CLASSIFICATION Introduction In the previous chapter, we explored a class of regression models having particularly simple analytical

More information

Chapter 4: Artificial Neural Networks

Chapter 4: Artificial Neural Networks Chapter 4: Artificial Neural Networks CS 536: Machine Learning Littman (Wu, TA) Administration icml-03: instructional Conference on Machine Learning http://www.cs.rutgers.edu/~mlittman/courses/ml03/icml03/

More information

NEURAL NETWORKS A Comprehensive Foundation

NEURAL NETWORKS A Comprehensive Foundation NEURAL NETWORKS A Comprehensive Foundation Second Edition Simon Haykin McMaster University Hamilton, Ontario, Canada Prentice Hall Prentice Hall Upper Saddle River; New Jersey 07458 Preface xii Acknowledgments

More information

Feed-Forward mapping networks KAIST 바이오및뇌공학과 정재승

Feed-Forward mapping networks KAIST 바이오및뇌공학과 정재승 Feed-Forward mapping networks KAIST 바이오및뇌공학과 정재승 How much energy do we need for brain functions? Information processing: Trade-off between energy consumption and wiring cost Trade-off between energy consumption

More information

Lecture 8 February 4

Lecture 8 February 4 ICS273A: Machine Learning Winter 2008 Lecture 8 February 4 Scribe: Carlos Agell (Student) Lecturer: Deva Ramanan 8.1 Neural Nets 8.1.1 Logistic Regression Recall the logistic function: g(x) = 1 1 + e θt

More information

Recurrent Neural Networks

Recurrent Neural Networks Recurrent Neural Networks Neural Computation : Lecture 12 John A. Bullinaria, 2015 1. Recurrent Neural Network Architectures 2. State Space Models and Dynamical Systems 3. Backpropagation Through Time

More information

Statistical Machine Learning

Statistical Machine Learning Statistical Machine Learning UoC Stats 37700, Winter quarter Lecture 4: classical linear and quadratic discriminants. 1 / 25 Linear separation For two classes in R d : simple idea: separate the classes

More information

Introduction to Machine Learning Using Python. Vikram Kamath

Introduction to Machine Learning Using Python. Vikram Kamath Introduction to Machine Learning Using Python Vikram Kamath Contents: 1. 2. 3. 4. 5. 6. 7. 8. 9. 10. Introduction/Definition Where and Why ML is used Types of Learning Supervised Learning Linear Regression

More information

IFT3395/6390. Machine Learning from linear regression to Neural Networks. Machine Learning. Training Set. t (3.5, -2,..., 127, 0,...

IFT3395/6390. Machine Learning from linear regression to Neural Networks. Machine Learning. Training Set. t (3.5, -2,..., 127, 0,... IFT3395/6390 Historical perspective: back to 1957 (Prof. Pascal Vincent) (Rosenblatt, Perceptron ) Machine Learning from linear regression to Neural Networks Computer Science Artificial Intelligence Symbolic

More information

Neural Networks and Back Propagation Algorithm

Neural Networks and Back Propagation Algorithm Neural Networks and Back Propagation Algorithm Mirza Cilimkovic Institute of Technology Blanchardstown Blanchardstown Road North Dublin 15 Ireland mirzac@gmail.com Abstract Neural Networks (NN) are important

More information

Introduction to Artificial Neural Networks

Introduction to Artificial Neural Networks POLYTECHNIC UNIVERSITY Department of Computer and Information Science Introduction to Artificial Neural Networks K. Ming Leung Abstract: A computing paradigm known as artificial neural network is introduced.

More information

3 An Illustrative Example

3 An Illustrative Example Objectives An Illustrative Example Objectives - Theory and Examples -2 Problem Statement -2 Perceptron - Two-Input Case -4 Pattern Recognition Example -5 Hamming Network -8 Feedforward Layer -8 Recurrent

More information

Neural Network Design in Cloud Computing

Neural Network Design in Cloud Computing International Journal of Computer Trends and Technology- volume4issue2-2013 ABSTRACT: Neural Network Design in Cloud Computing B.Rajkumar #1,T.Gopikiran #2,S.Satyanarayana *3 #1,#2Department of Computer

More information

Linear smoother. ŷ = S y. where s ij = s ij (x) e.g. s ij = diag(l i (x)) To go the other way, you need to diagonalize S

Linear smoother. ŷ = S y. where s ij = s ij (x) e.g. s ij = diag(l i (x)) To go the other way, you need to diagonalize S Linear smoother ŷ = S y where s ij = s ij (x) e.g. s ij = diag(l i (x)) To go the other way, you need to diagonalize S 2 Online Learning: LMS and Perceptrons Partially adapted from slides by Ryan Gabbard

More information

Data Mining. Supervised Methods. Ciro Donalek donalek@astro.caltech.edu. Ay/Bi 199ab: Methods of Computa@onal Sciences hcp://esci101.blogspot.

Data Mining. Supervised Methods. Ciro Donalek donalek@astro.caltech.edu. Ay/Bi 199ab: Methods of Computa@onal Sciences hcp://esci101.blogspot. Data Mining Supervised Methods Ciro Donalek donalek@astro.caltech.edu Supervised Methods Summary Ar@ficial Neural Networks Mul@layer Perceptron Support Vector Machines SoLwares Supervised Models: Supervised

More information

Neural network software tool development: exploring programming language options

Neural network software tool development: exploring programming language options INEB- PSI Technical Report 2006-1 Neural network software tool development: exploring programming language options Alexandra Oliveira aao@fe.up.pt Supervisor: Professor Joaquim Marques de Sá June 2006

More information

Stock Prediction using Artificial Neural Networks

Stock Prediction using Artificial Neural Networks Stock Prediction using Artificial Neural Networks Abhishek Kar (Y8021), Dept. of Computer Science and Engineering, IIT Kanpur Abstract In this work we present an Artificial Neural Network approach to predict

More information

NEURAL NETWORK FUNDAMENTALS WITH GRAPHS, ALGORITHMS, AND APPLICATIONS

NEURAL NETWORK FUNDAMENTALS WITH GRAPHS, ALGORITHMS, AND APPLICATIONS NEURAL NETWORK FUNDAMENTALS WITH GRAPHS, ALGORITHMS, AND APPLICATIONS N. K. Bose HRB-Systems Professor of Electrical Engineering The Pennsylvania State University, University Park P. Liang Associate Professor

More information

Biological Neurons and Neural Networks, Artificial Neurons

Biological Neurons and Neural Networks, Artificial Neurons Biological Neurons and Neural Networks, Artificial Neurons Neural Computation : Lecture 2 John A. Bullinaria, 2015 1. Organization of the Nervous System and Brain 2. Brains versus Computers: Some Numbers

More information

A Simple Feature Extraction Technique of a Pattern By Hopfield Network

A Simple Feature Extraction Technique of a Pattern By Hopfield Network A Simple Feature Extraction Technique of a Pattern By Hopfield Network A.Nag!, S. Biswas *, D. Sarkar *, P.P. Sarkar *, B. Gupta **! Academy of Technology, Hoogly - 722 *USIC, University of Kalyani, Kalyani

More information

Linear Threshold Units

Linear Threshold Units Linear Threshold Units w x hx (... w n x n w We assume that each feature x j and each weight w j is a real number (we will relax this later) We will study three different algorithms for learning linear

More information

A Simple Introduction to Support Vector Machines

A Simple Introduction to Support Vector Machines A Simple Introduction to Support Vector Machines Martin Law Lecture for CSE 802 Department of Computer Science and Engineering Michigan State University Outline A brief history of SVM Large-margin linear

More information

Predictive Dynamix Inc

Predictive Dynamix Inc Predictive Modeling Technology Predictive modeling is concerned with analyzing patterns and trends in historical and operational data in order to transform data into actionable decisions. This is accomplished

More information

Big Data Analytics CSCI 4030

Big Data Analytics CSCI 4030 High dim. data Graph data Infinite data Machine learning Apps Locality sensitive hashing PageRank, SimRank Filtering data streams SVM Recommen der systems Clustering Community Detection Web advertising

More information

Learning to Process Natural Language in Big Data Environment

Learning to Process Natural Language in Big Data Environment CCF ADL 2015 Nanchang Oct 11, 2015 Learning to Process Natural Language in Big Data Environment Hang Li Noah s Ark Lab Huawei Technologies Part 1: Deep Learning - Present and Future Talk Outline Overview

More information

Linear Models for Classification

Linear Models for Classification Linear Models for Classification Sumeet Agarwal, EEL709 (Most figures from Bishop, PRML) Approaches to classification Discriminant function: Directly assigns each data point x to a particular class Ci

More information

Neural Networks in Data Mining

Neural Networks in Data Mining IOSR Journal of Engineering (IOSRJEN) ISSN (e): 2250-3021, ISSN (p): 2278-8719 Vol. 04, Issue 03 (March. 2014), V6 PP 01-06 www.iosrjen.org Neural Networks in Data Mining Ripundeep Singh Gill, Ashima Department

More information

NEUROMATHEMATICS: DEVELOPMENT TENDENCIES. 1. Which tasks are adequate of neurocomputers?

NEUROMATHEMATICS: DEVELOPMENT TENDENCIES. 1. Which tasks are adequate of neurocomputers? Appl. Comput. Math. 2 (2003), no. 1, pp. 57-64 NEUROMATHEMATICS: DEVELOPMENT TENDENCIES GALUSHKIN A.I., KOROBKOVA. S.V., KAZANTSEV P.A. Abstract. This article is the summary of a set of Russian scientists

More information

How To Use Neural Networks In Data Mining

How To Use Neural Networks In Data Mining International Journal of Electronics and Computer Science Engineering 1449 Available Online at www.ijecse.org ISSN- 2277-1956 Neural Networks in Data Mining Priyanka Gaur Department of Information and

More information

Self Organizing Maps: Fundamentals

Self Organizing Maps: Fundamentals Self Organizing Maps: Fundamentals Introduction to Neural Networks : Lecture 16 John A. Bullinaria, 2004 1. What is a Self Organizing Map? 2. Topographic Maps 3. Setting up a Self Organizing Map 4. Kohonen

More information

TRAINING A LIMITED-INTERCONNECT, SYNTHETIC NEURAL IC

TRAINING A LIMITED-INTERCONNECT, SYNTHETIC NEURAL IC 777 TRAINING A LIMITED-INTERCONNECT, SYNTHETIC NEURAL IC M.R. Walker. S. Haghighi. A. Afghan. and L.A. Akers Center for Solid State Electronics Research Arizona State University Tempe. AZ 85287-6206 mwalker@enuxha.eas.asu.edu

More information

New Work Item for ISO 3534-5 Predictive Analytics (Initial Notes and Thoughts) Introduction

New Work Item for ISO 3534-5 Predictive Analytics (Initial Notes and Thoughts) Introduction Introduction New Work Item for ISO 3534-5 Predictive Analytics (Initial Notes and Thoughts) Predictive analytics encompasses the body of statistical knowledge supporting the analysis of massive data sets.

More information

INTELLIGENT ENERGY MANAGEMENT OF ELECTRICAL POWER SYSTEMS WITH DISTRIBUTED FEEDING ON THE BASIS OF FORECASTS OF DEMAND AND GENERATION Chr.

INTELLIGENT ENERGY MANAGEMENT OF ELECTRICAL POWER SYSTEMS WITH DISTRIBUTED FEEDING ON THE BASIS OF FORECASTS OF DEMAND AND GENERATION Chr. INTELLIGENT ENERGY MANAGEMENT OF ELECTRICAL POWER SYSTEMS WITH DISTRIBUTED FEEDING ON THE BASIS OF FORECASTS OF DEMAND AND GENERATION Chr. Meisenbach M. Hable G. Winkler P. Meier Technology, Laboratory

More information

Artificial neural networks

Artificial neural networks Artificial neural networks Now Neurons Neuron models Perceptron learning Multi-layer perceptrons Backpropagation 2 It all starts with a neuron 3 Some facts about human brain ~ 86 billion neurons ~ 10 15

More information

Data Mining and Neural Networks in Stata

Data Mining and Neural Networks in Stata Data Mining and Neural Networks in Stata 2 nd Italian Stata Users Group Meeting Milano, 10 October 2005 Mario Lucchini e Maurizo Pisati Università di Milano-Bicocca mario.lucchini@unimib.it maurizio.pisati@unimib.it

More information

Simple and efficient online algorithms for real world applications

Simple and efficient online algorithms for real world applications Simple and efficient online algorithms for real world applications Università degli Studi di Milano Milano, Italy Talk @ Centro de Visión por Computador Something about me PhD in Robotics at LIRA-Lab,

More information

SUCCESSFUL PREDICTION OF HORSE RACING RESULTS USING A NEURAL NETWORK

SUCCESSFUL PREDICTION OF HORSE RACING RESULTS USING A NEURAL NETWORK SUCCESSFUL PREDICTION OF HORSE RACING RESULTS USING A NEURAL NETWORK N M Allinson and D Merritt 1 Introduction This contribution has two main sections. The first discusses some aspects of multilayer perceptrons,

More information

A Time Series ANN Approach for Weather Forecasting

A Time Series ANN Approach for Weather Forecasting A Time Series ANN Approach for Weather Forecasting Neeraj Kumar 1, Govind Kumar Jha 2 1 Associate Professor and Head Deptt. Of Computer Science,Nalanda College Of Engineering Chandi(Bihar) 2 Assistant

More information

6.2.8 Neural networks for data mining

6.2.8 Neural networks for data mining 6.2.8 Neural networks for data mining Walter Kosters 1 In many application areas neural networks are known to be valuable tools. This also holds for data mining. In this chapter we discuss the use of neural

More information

Advanced analytics at your hands

Advanced analytics at your hands 2.3 Advanced analytics at your hands Neural Designer is the most powerful predictive analytics software. It uses innovative neural networks techniques to provide data scientists with results in a way previously

More information

The Impact of Big Data on Classic Machine Learning Algorithms. Thomas Jensen, Senior Business Analyst @ Expedia

The Impact of Big Data on Classic Machine Learning Algorithms. Thomas Jensen, Senior Business Analyst @ Expedia The Impact of Big Data on Classic Machine Learning Algorithms Thomas Jensen, Senior Business Analyst @ Expedia Who am I? Senior Business Analyst @ Expedia Working within the competitive intelligence unit

More information

EFFICIENT DATA PRE-PROCESSING FOR DATA MINING

EFFICIENT DATA PRE-PROCESSING FOR DATA MINING EFFICIENT DATA PRE-PROCESSING FOR DATA MINING USING NEURAL NETWORKS JothiKumar.R 1, Sivabalan.R.V 2 1 Research scholar, Noorul Islam University, Nagercoil, India Assistant Professor, Adhiparasakthi College

More information

Analecta Vol. 8, No. 2 ISSN 2064-7964

Analecta Vol. 8, No. 2 ISSN 2064-7964 EXPERIMENTAL APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS IN ENGINEERING PROCESSING SYSTEM S. Dadvandipour Institute of Information Engineering, University of Miskolc, Egyetemváros, 3515, Miskolc, Hungary,

More information

Role of Neural network in data mining

Role of Neural network in data mining Role of Neural network in data mining Chitranjanjit kaur Associate Prof Guru Nanak College, Sukhchainana Phagwara,(GNDU) Punjab, India Pooja kapoor Associate Prof Swami Sarvanand Group Of Institutes Dinanagar(PTU)

More information

These slides follow closely the (English) course textbook Pattern Recognition and Machine Learning by Christopher Bishop

These slides follow closely the (English) course textbook Pattern Recognition and Machine Learning by Christopher Bishop Music and Machine Learning (IFT6080 Winter 08) Prof. Douglas Eck, Université de Montréal These slides follow closely the (English) course textbook Pattern Recognition and Machine Learning by Christopher

More information

Neural Networks algorithms and applications

Neural Networks algorithms and applications Neural Networks algorithms and applications By Fiona Nielsen 4i 12/12-2001 Supervisor: Geert Rasmussen Niels Brock Business College 1 Introduction Neural Networks is a field of Artificial Intelligence

More information

Chapter 12 Discovering New Knowledge Data Mining

Chapter 12 Discovering New Knowledge Data Mining Chapter 12 Discovering New Knowledge Data Mining Becerra-Fernandez, et al. -- Knowledge Management 1/e -- 2004 Prentice Hall Additional material 2007 Dekai Wu Chapter Objectives Introduce the student to

More information

Power Prediction Analysis using Artificial Neural Network in MS Excel

Power Prediction Analysis using Artificial Neural Network in MS Excel Power Prediction Analysis using Artificial Neural Network in MS Excel NURHASHINMAH MAHAMAD, MUHAMAD KAMAL B. MOHAMMED AMIN Electronic System Engineering Department Malaysia Japan International Institute

More information

Deep Learning for Multivariate Financial Time Series. Gilberto Batres-Estrada

Deep Learning for Multivariate Financial Time Series. Gilberto Batres-Estrada Deep Learning for Multivariate Financial Time Series Gilberto Batres-Estrada June 4, 2015 Abstract Deep learning is a framework for training and modelling neural networks which recently have surpassed

More information

Programming Exercise 3: Multi-class Classification and Neural Networks

Programming Exercise 3: Multi-class Classification and Neural Networks Programming Exercise 3: Multi-class Classification and Neural Networks Machine Learning November 4, 2011 Introduction In this exercise, you will implement one-vs-all logistic regression and neural networks

More information

SELECTING NEURAL NETWORK ARCHITECTURE FOR INVESTMENT PROFITABILITY PREDICTIONS

SELECTING NEURAL NETWORK ARCHITECTURE FOR INVESTMENT PROFITABILITY PREDICTIONS UDC: 004.8 Original scientific paper SELECTING NEURAL NETWORK ARCHITECTURE FOR INVESTMENT PROFITABILITY PREDICTIONS Tonimir Kišasondi, Alen Lovren i University of Zagreb, Faculty of Organization and Informatics,

More information

Novelty Detection in image recognition using IRF Neural Networks properties

Novelty Detection in image recognition using IRF Neural Networks properties Novelty Detection in image recognition using IRF Neural Networks properties Philippe Smagghe, Jean-Luc Buessler, Jean-Philippe Urban Université de Haute-Alsace MIPS 4, rue des Frères Lumière, 68093 Mulhouse,

More information

Neural Networks in Quantitative Finance

Neural Networks in Quantitative Finance Neural Networks in Quantitative Finance Master Thesis submitted to Prof. Dr. Wolfgang Härdle Institute for Statistics and Econometrics CASE - Center for Applied Statistics and Economics Humboldt-Universität

More information

An Introduction to Neural Networks

An Introduction to Neural Networks An Introduction to Vincent Cheung Kevin Cannons Signal & Data Compression Laboratory Electrical & Computer Engineering University of Manitoba Winnipeg, Manitoba, Canada Advisor: Dr. W. Kinsner May 27,

More information

Computational Intelligence Introduction

Computational Intelligence Introduction Computational Intelligence Introduction Farzaneh Abdollahi Department of Electrical Engineering Amirkabir University of Technology Fall 2011 Farzaneh Abdollahi Neural Networks 1/21 Fuzzy Systems What are

More information

Data Mining Using Neural Networks: A Guide for Statisticians

Data Mining Using Neural Networks: A Guide for Statisticians Data Mining Using Neural Networks: A Guide for Statisticians Basilio de Bragança Pereira UFRJ - Universidade Federal do Rio de Janeiro Calyampudi Radhakrishna Rao PSU - Penn State University June 2009

More information

degrees of freedom and are able to adapt to the task they are supposed to do [Gupta].

degrees of freedom and are able to adapt to the task they are supposed to do [Gupta]. 1.3 Neural Networks 19 Neural Networks are large structured systems of equations. These systems have many degrees of freedom and are able to adapt to the task they are supposed to do [Gupta]. Two very

More information

Machine Learning: Multi Layer Perceptrons

Machine Learning: Multi Layer Perceptrons Machine Learning: Multi Layer Perceptrons Prof. Dr. Martin Riedmiller Albert-Ludwigs-University Freiburg AG Maschinelles Lernen Machine Learning: Multi Layer Perceptrons p.1/61 Outline multi layer perceptrons

More information

Data Mining and Data Warehousing. Henryk Maciejewski. Data Mining Predictive modelling: regression

Data Mining and Data Warehousing. Henryk Maciejewski. Data Mining Predictive modelling: regression Data Mining and Data Warehousing Henryk Maciejewski Data Mining Predictive modelling: regression Algorithms for Predictive Modelling Contents Regression Classification Auxiliary topics: Estimation of prediction

More information

AN APPLICATION OF TIME SERIES ANALYSIS FOR WEATHER FORECASTING

AN APPLICATION OF TIME SERIES ANALYSIS FOR WEATHER FORECASTING AN APPLICATION OF TIME SERIES ANALYSIS FOR WEATHER FORECASTING Abhishek Agrawal*, Vikas Kumar** 1,Ashish Pandey** 2,Imran Khan** 3 *(M. Tech Scholar, Department of Computer Science, Bhagwant University,

More information

Data quality in Accounting Information Systems

Data quality in Accounting Information Systems Data quality in Accounting Information Systems Comparing Several Data Mining Techniques Erjon Zoto Department of Statistics and Applied Informatics Faculty of Economy, University of Tirana Tirana, Albania

More information

Machine Learning and Data Mining -

Machine Learning and Data Mining - Machine Learning and Data Mining - Perceptron Neural Networks Nuno Cavalheiro Marques (nmm@di.fct.unl.pt) Spring Semester 2010/2011 MSc in Computer Science Multi Layer Perceptron Neurons and the Perceptron

More information

Modern Optimization Methods for Big Data Problems MATH11146 The University of Edinburgh

Modern Optimization Methods for Big Data Problems MATH11146 The University of Edinburgh Modern Optimization Methods for Big Data Problems MATH11146 The University of Edinburgh Peter Richtárik Week 3 Randomized Coordinate Descent With Arbitrary Sampling January 27, 2016 1 / 30 The Problem

More information

Modelling and Big Data. Leslie Smith ITNPBD4, October 10 2015. Updated 9 October 2015

Modelling and Big Data. Leslie Smith ITNPBD4, October 10 2015. Updated 9 October 2015 Modelling and Big Data Leslie Smith ITNPBD4, October 10 2015. Updated 9 October 2015 Big data and Models: content What is a model in this context (and why the context matters) Explicit models Mathematical

More information

Method of Combining the Degrees of Similarity in Handwritten Signature Authentication Using Neural Networks

Method of Combining the Degrees of Similarity in Handwritten Signature Authentication Using Neural Networks Method of Combining the Degrees of Similarity in Handwritten Signature Authentication Using Neural Networks Ph. D. Student, Eng. Eusebiu Marcu Abstract This paper introduces a new method of combining the

More information

TRAIN AND ANALYZE NEURAL NETWORKS TO FIT YOUR DATA

TRAIN AND ANALYZE NEURAL NETWORKS TO FIT YOUR DATA TRAIN AND ANALYZE NEURAL NETWORKS TO FIT YOUR DATA TRAIN AND ANALYZE NEURAL NETWORKS TO FIT YOUR DATA September 2005 First edition Intended for use with Mathematica 5 Software and manual written by: Jonas

More information

THREE DIMENSIONAL REPRESENTATION OF AMINO ACID CHARAC- TERISTICS

THREE DIMENSIONAL REPRESENTATION OF AMINO ACID CHARAC- TERISTICS THREE DIMENSIONAL REPRESENTATION OF AMINO ACID CHARAC- TERISTICS O.U. Sezerman 1, R. Islamaj 2, E. Alpaydin 2 1 Laborotory of Computational Biology, Sabancı University, Istanbul, Turkey. 2 Computer Engineering

More information

CS 688 Pattern Recognition Lecture 4. Linear Models for Classification

CS 688 Pattern Recognition Lecture 4. Linear Models for Classification CS 688 Pattern Recognition Lecture 4 Linear Models for Classification Probabilistic generative models Probabilistic discriminative models 1 Generative Approach ( x ) p C k p( C k ) Ck p ( ) ( x Ck ) p(

More information

Parallel & Distributed Optimization. Based on Mark Schmidt s slides

Parallel & Distributed Optimization. Based on Mark Schmidt s slides Parallel & Distributed Optimization Based on Mark Schmidt s slides Motivation behind using parallel & Distributed optimization Performance Computational throughput have increased exponentially in linear

More information

Machine Learning. CUNY Graduate Center, Spring 2013. Professor Liang Huang. huang@cs.qc.cuny.edu

Machine Learning. CUNY Graduate Center, Spring 2013. Professor Liang Huang. huang@cs.qc.cuny.edu Machine Learning CUNY Graduate Center, Spring 2013 Professor Liang Huang huang@cs.qc.cuny.edu http://acl.cs.qc.edu/~lhuang/teaching/machine-learning Logistics Lectures M 9:30-11:30 am Room 4419 Personnel

More information

Logistic Regression. Vibhav Gogate The University of Texas at Dallas. Some Slides from Carlos Guestrin, Luke Zettlemoyer and Dan Weld.

Logistic Regression. Vibhav Gogate The University of Texas at Dallas. Some Slides from Carlos Guestrin, Luke Zettlemoyer and Dan Weld. Logistic Regression Vibhav Gogate The University of Texas at Dallas Some Slides from Carlos Guestrin, Luke Zettlemoyer and Dan Weld. Generative vs. Discriminative Classifiers Want to Learn: h:x Y X features

More information

THE HUMAN BRAIN. observations and foundations

THE HUMAN BRAIN. observations and foundations THE HUMAN BRAIN observations and foundations brains versus computers a typical brain contains something like 100 billion miniscule cells called neurons estimates go from about 50 billion to as many as

More information

Analysis of Multilayer Neural Networks with Direct and Cross-Forward Connection

Analysis of Multilayer Neural Networks with Direct and Cross-Forward Connection Analysis of Multilayer Neural Networks with Direct and Cross-Forward Connection Stanis law P laczek and Bijaya Adhikari Vistula University, Warsaw, Poland stanislaw.placzek@wp.pl,bijaya.adhikari1991@gmail.com

More information

A simple application of Artificial Neural Network to cloud classification

A simple application of Artificial Neural Network to cloud classification A simple application of Artificial Neural Network to cloud classification Tianle Yuan For AOSC 630 (by Prof. Kalnay) Introduction to Pattern Recognition (PR) Example1: visual separation between the character

More information

Tolerance of Radial Basis Functions against Stuck-At-Faults

Tolerance of Radial Basis Functions against Stuck-At-Faults Tolerance of Radial Basis Functions against Stuck-At-Faults Ralf Eickhoff 1 and Ulrich Rückert 1 Heinz Nixdorf Institute System and Circuit Technology University of Paderborn, Germany eickhoff,rueckert@hni.upb.de

More information

STA 4273H: Statistical Machine Learning

STA 4273H: Statistical Machine Learning STA 4273H: Statistical Machine Learning Russ Salakhutdinov Department of Statistics! rsalakhu@utstat.toronto.edu! http://www.cs.toronto.edu/~rsalakhu/ Lecture 6 Three Approaches to Classification Construct

More information

Machine Learning Logistic Regression

Machine Learning Logistic Regression Machine Learning Logistic Regression Jeff Howbert Introduction to Machine Learning Winter 2012 1 Logistic regression Name is somewhat misleading. Really a technique for classification, not regression.

More information

Feature Subset Selection in E-mail Spam Detection

Feature Subset Selection in E-mail Spam Detection Feature Subset Selection in E-mail Spam Detection Amir Rajabi Behjat, Universiti Technology MARA, Malaysia IT Security for the Next Generation Asia Pacific & MEA Cup, Hong Kong 14-16 March, 2012 Feature

More information

Wes, Delaram, and Emily MA751. Exercise 4.5. 1 p(x; β) = [1 p(xi ; β)] = 1 p(x. y i [βx i ] log [1 + exp {βx i }].

Wes, Delaram, and Emily MA751. Exercise 4.5. 1 p(x; β) = [1 p(xi ; β)] = 1 p(x. y i [βx i ] log [1 + exp {βx i }]. Wes, Delaram, and Emily MA75 Exercise 4.5 Consider a two-class logistic regression problem with x R. Characterize the maximum-likelihood estimates of the slope and intercept parameter if the sample for

More information

Predict Influencers in the Social Network

Predict Influencers in the Social Network Predict Influencers in the Social Network Ruishan Liu, Yang Zhao and Liuyu Zhou Email: rliu2, yzhao2, lyzhou@stanford.edu Department of Electrical Engineering, Stanford University Abstract Given two persons

More information

ANN Based Fault Classifier and Fault Locator for Double Circuit Transmission Line

ANN Based Fault Classifier and Fault Locator for Double Circuit Transmission Line International Journal of Computer Sciences and Engineering Open Access Research Paper Volume-4, Special Issue-2, April 2016 E-ISSN: 2347-2693 ANN Based Fault Classifier and Fault Locator for Double Circuit

More information

Prediction Model for Crude Oil Price Using Artificial Neural Networks

Prediction Model for Crude Oil Price Using Artificial Neural Networks Applied Mathematical Sciences, Vol. 8, 2014, no. 80, 3953-3965 HIKARI Ltd, www.m-hikari.com http://dx.doi.org/10.12988/ams.2014.43193 Prediction Model for Crude Oil Price Using Artificial Neural Networks

More information

Comparison of Supervised and Unsupervised Learning Classifiers for Travel Recommendations

Comparison of Supervised and Unsupervised Learning Classifiers for Travel Recommendations Volume 3, No. 8, August 2012 Journal of Global Research in Computer Science REVIEW ARTICLE Available Online at www.jgrcs.info Comparison of Supervised and Unsupervised Learning Classifiers for Travel Recommendations

More information

APPLICATION OF ARTIFICIAL NEURAL NETWORKS USING HIJRI LUNAR TRANSACTION AS EXTRACTED VARIABLES TO PREDICT STOCK TREND DIRECTION

APPLICATION OF ARTIFICIAL NEURAL NETWORKS USING HIJRI LUNAR TRANSACTION AS EXTRACTED VARIABLES TO PREDICT STOCK TREND DIRECTION LJMS 2008, 2 Labuan e-journal of Muamalat and Society, Vol. 2, 2008, pp. 9-16 Labuan e-journal of Muamalat and Society APPLICATION OF ARTIFICIAL NEURAL NETWORKS USING HIJRI LUNAR TRANSACTION AS EXTRACTED

More information

Artificial Neural Networks are bio-inspired mechanisms for intelligent decision support. Artificial Neural Networks. Research Article 2014

Artificial Neural Networks are bio-inspired mechanisms for intelligent decision support. Artificial Neural Networks. Research Article 2014 An Experiment to Signify Fuzzy Logic as an Effective User Interface Tool for Artificial Neural Network Nisha Macwan *, Priti Srinivas Sajja G.H. Patel Department of Computer Science India Abstract Artificial

More information

Lecture 3: Linear methods for classification

Lecture 3: Linear methods for classification Lecture 3: Linear methods for classification Rafael A. Irizarry and Hector Corrada Bravo February, 2010 Today we describe four specific algorithms useful for classification problems: linear regression,

More information

A Neural Support Vector Network Architecture with Adaptive Kernels. 1 Introduction. 2 Support Vector Machines and Motivations

A Neural Support Vector Network Architecture with Adaptive Kernels. 1 Introduction. 2 Support Vector Machines and Motivations A Neural Support Vector Network Architecture with Adaptive Kernels Pascal Vincent & Yoshua Bengio Département d informatique et recherche opérationnelle Université de Montréal C.P. 6128 Succ. Centre-Ville,

More information

Performance Evaluation of Artificial Neural. Networks for Spatial Data Analysis

Performance Evaluation of Artificial Neural. Networks for Spatial Data Analysis Contemporary Engineering Sciences, Vol. 4, 2011, no. 4, 149-163 Performance Evaluation of Artificial Neural Networks for Spatial Data Analysis Akram A. Moustafa Department of Computer Science Al al-bayt

More information

Follow links Class Use and other Permissions. For more information, send email to: permissions@pupress.princeton.edu

Follow links Class Use and other Permissions. For more information, send email to: permissions@pupress.princeton.edu COPYRIGHT NOTICE: David A. Kendrick, P. Ruben Mercado, and Hans M. Amman: Computational Economics is published by Princeton University Press and copyrighted, 2006, by Princeton University Press. All rights

More information

Applications to Data Smoothing and Image Processing I

Applications to Data Smoothing and Image Processing I Applications to Data Smoothing and Image Processing I MA 348 Kurt Bryan Signals and Images Let t denote time and consider a signal a(t) on some time interval, say t. We ll assume that the signal a(t) is

More information

PLAANN as a Classification Tool for Customer Intelligence in Banking

PLAANN as a Classification Tool for Customer Intelligence in Banking PLAANN as a Classification Tool for Customer Intelligence in Banking EUNITE World Competition in domain of Intelligent Technologies The Research Report Ireneusz Czarnowski and Piotr Jedrzejowicz Department

More information

Implementation of Neural Networks with Theano. http://deeplearning.net/tutorial/

Implementation of Neural Networks with Theano. http://deeplearning.net/tutorial/ Implementation of Neural Networks with Theano http://deeplearning.net/tutorial/ Feed Forward Neural Network (MLP) Hidden Layer Object Hidden Layer Object Hidden Layer Object Logistic Regression Object

More information

Data Mining mit der JMSL Numerical Library for Java Applications

Data Mining mit der JMSL Numerical Library for Java Applications Data Mining mit der JMSL Numerical Library for Java Applications Stefan Sineux 8. Java Forum Stuttgart 07.07.2005 Agenda Visual Numerics JMSL TM Numerical Library Neuronale Netze (Hintergrund) Demos Neuronale

More information

Operations Research and Knowledge Modeling in Data Mining

Operations Research and Knowledge Modeling in Data Mining Operations Research and Knowledge Modeling in Data Mining Masato KODA Graduate School of Systems and Information Engineering University of Tsukuba, Tsukuba Science City, Japan 305-8573 koda@sk.tsukuba.ac.jp

More information

Machine Learning in FX Carry Basket Prediction

Machine Learning in FX Carry Basket Prediction Machine Learning in FX Carry Basket Prediction Tristan Fletcher, Fabian Redpath and Joe D Alessandro Abstract Artificial Neural Networks ANN), Support Vector Machines SVM) and Relevance Vector Machines

More information