AI and and Brain Science Toward Mathematical Theory of MLP

Size: px
Start display at page:

Download "AI and and Brain Science Toward Mathematical Theory of MLP"

Transcription

1 First Japan Korea Machine Learning Symposium AI and and Brain Science Toward Mathematical Theory of MLP Shun ichi Amari RIKEN Brain Science Institute Principles of the Brain many neurons connected (network) parallel dynamics learning through synaptic plasticity

2 Brain has found and implemented the principles through evolution (random search) historical restriction material restriction Very complex (not smartly designed)

3 Mathematical Neuroscience searches for the principles mathematical studies using simple idealistic models (not realistic) Computational neuroscience AI : technological realization

4 Brief History of AI and BT First Boom 1950~ AI BT Dartmous Conf. Perceptron symbol universal computation logic learning machine Dark period (late 1960~1970 s) stochastic descent learning (1967) for MLP

5 First stochastic descent learning of MLP (1967;1968) Information Theory II Geometrical Theory of Information Shun ichi Amari University of Tokyo Kyoritu Press, Tokyo, 1968

6

7 x, max w xw, x min w xw, x f v v w 1 max x v 1 y w 4 max v 2

8 Second Boom 1970~ AI 1980~ BT (neural networks) expert system MLP (backprop) (MYCIN) associative memory stochastic inference (Bayes) chess (1997)

9 Third Boom 2000~ Deep learning Stochastic inference (graphical model; Bayesian; WATSON) Deep learning pattern recognition: vision, auditory, sentence analysis shougi (Japanese chess; alpha go) Language processing; sequence and dynamics (word2vec, deep learning with rec. net) Integration of (symbol, logic) vs (pattern, dynamics)

10 Human Brain: Consciousness symbol logic pattern dynamics

11 Libet experiment: Free Will EEG When!

12 Prediction and Postdiction dual dynamics conscious Dynamics decision and action justification, logical reasoning

13 Deep learning Pattern dynamics symbol, sentence, logic (prediction) Learning conscious machine: postdiction

14 Future AI and BT Postdiction: logic symbol, logic pattern dynamics Associative memory AI gives the existence proof of the principles AI and BT searching for the same principles different implementation

15 Mathematical Theory of Multilayer Perceptrons Dynamics of Self Organization and Singularities in Supervised Learning Towards Understanding Deep Learning Shun ichi Amari RIKEN Brain Science Institute collaborator R. Karakida (U Tokyo)

16 Deep Learning Self Organization + Supervised Learning RBM: Restricted Boltzmann Machine Auto Encoder, Recurrent Net Dropout Contrastive divergence convolution

17 Simple Hebbian Self Organization : p( v)

18 self organization of

19 Equillibrium

20 Equillibrium: special cases

21 Two and many clusters

22 Dynamics of self organization

23 Lyapunov Function

24 Further Problems Dimension reduction; PCA, ICA Distributed small clusters; large clusters Mutual interactions among h neurons neural field Localized receptive fields invariance: convolution

25 RBM: Restricted Boltzmann Machine

26 Self Organization

27 Interaction of Hidden Neurons

28

29 Recurrent Net (Auto Encoder)

30 Gaussian Boltzmann Machine

31 Equilibrium Solution (R. Karakida) General Solution othogonal matrix, diagonalized by You can choose m( k) eigen values form Stable Solution the case of m = k

32 Bernoulli Gaussian RBM ICA R. Karakida

33 Equilibrium Analysis: Results Assumption of Input s: Independent and nonnegative sources B: N N orthogonal matrix ICA (independent Component Analysis) Solutions If, ML and CD learning have the following stable solutions: W s Space Mean value: Model variance : σ CD Solutions ICA ML Solutions 33

34 Simulation The number of Neurons: N = M = 2, σ = 1/2 Sources p (s) Uniform Distribution Mixing Input CD ICA Solution Output Independent sources are extracted in G B RBM 34

35 Structure of environment: good model Uniform : no structure Aggregate of clusters : Hebb self organization PCA : Gaussian RBM submanifolds ICA : Bernoulli Gaussain sparse Hierarchy : deep learning invariancy logical structure hierarchies of hierarchy

36 Supervised Learning Multilayer perceptron Back prop learning Singularity!! Natural Gradient Solves Difficulty

37 Mathematical Neurons y wx h i i w x x ( u) y u

38 Multilayer Perceptrons y v i wi x w 1 x x ( x1, x2,..., x n ) x y f x v w x, i i ( w,..., w ; v,..., v ) 1 m 1 m

39 Multilayer Perceptron neuromanifold () x space of functions S y f x, θ v i w i x θ v, v ; w, w 1 m 1, m

40 Backpropagation --- stochastic gradient learning x x examples :,,, training set y1 1 y t t 1 l( y, x; ) y f x, 2 log p y, x; 2 l( yt, xt; t) t t f x, v w x i i

41 singularities

42 Geometry of singular model y v wx n v v w 0 W

43 model: 2 hidden neurons f x, w J x w J x y f x, t 1 u 2 u e dt 2 2

44 1 loss function: l, y; y f, 2 x x 2 y : teacher signal : 0 stochastic descent learning l x, y, t t t backprop : vanilla gradient

45 Natural Gradient Stochastic Descent x, y, 1 G t t t t G l l : Fisher Information Matrix invarint; steepest descent

46 Natural Gradient (Riemannian) max dl l d l d 2 1 l G l lx (, y; ) t t t t t

47 Steepest Direction---Natural Gradient l( ) l l l,, 1 n 1 l G l 2 d i j d d Gd = G d d ij lx (, y; ) t t t t t

48 Natural gradient is superior Steepest descent; invariant Yan Ollivier Fisher efficient Natural gradient is non vanishing even in multiple layers Good at singular regions (avoid plateaus: Milnor attractor)

49 Adaptive Natural Gradient

50 Singular Region in Parameter Space R w w w w, J J J J, w 0, w w, J w w, w 0, J J J f x, w J x w J x

51 Coordinate transformation v w J w w J w , w w w 1 2, u J J 2 1, z w w w w v, w, u, z

52 Singular Region, J u0 z 1 R w

53 Singular lines in the parameter space

54 Taylor expansion u : small w f w z 8 2 x, vx vx 1 ux w 2 3 vx z 1z ux 24 2 fast dynamics w, v : stability slow dynamics u, z

55 neiborhood of R u w 2 1z eu xx 2 z z z e 4w solution:trajectory 2 3 u x z 3 u t w log c 2 3 z t 2 2

56 Stability 1 true solution is in R : R u 0 or z 1 : stable

57 Dynamic vector fields: Redundant case

58 Stability 2 : true solution is outside R H e T x xx wh : positive-definite z 1 stable ; z 1 unstable wh : negative-definite z 1 stable ; z 1 unstable

59 Learning Trajectory near the singularity

60 Milnor attractor

61 Dynamic vector fields: General case ( z >1 part stable )

62 Fig. 2: trajectories

63 Saddle and plateau

64 retardation of learning: plateau E 1 2 e 2 E E O u O u 5 2

65 Topology of singular R blow-down coordinates : =,, e 2 2 c1 1 z u, u u 2 cz z u 2 3 1, e u S, 1 n e u

66 Singular Region, J u0 z 1 R w

67

68 Sphere Sn and Projective space Pn

69 natural gradient learning near singularity d dt : true modelr d dt O 1 : true model R Milnor attractor

70 How to realize the natural gradient adaptive natural gradient G G G l lg t 1 1 t t t Unitwise diagonalization of G: Yan Olliver G 1 l : non-singular G: unitwise-diagonalization is OK (Ollivier)

71 Natural Gradient Learning Simple and Multilayer Perceptron y f x, 1 p q f 2 x, y; xexp y x 1 l log p, ; log q 2 x y x y f x 2 2 x f x, y e 1 2 y f x 2 G 1 e

72 Simple perceptron y wx u 2 0 exp v 2 1 u u exp 2 2 u 2 2 dv x w y l wx x w G 1 w E exp q xx wx 2 2

73 Fisher information matrix x 0, q N I G w I 1 2w 1 2w 2 ww 2 w 12 2ww 1 2 G w I l G l 12w e 2 exp 2 2 ElG l 1, w w x w xw w x 0 2

74 q x : singular u x ux 0 ug w u 0 : G singular x x w w u 1, 1, 0,, 0 w 1 w 2 x w y

75 MLP x z r z L y z 0 W W 1 2 W W r L 1 z r r r1 W z r 1,, L z 0 x y W L1 z y f x, W L W W,, W 1 L1

76 error back propagation e e W z, r 1,, L r r1 r r1 e y f x, W L1 0 Fisher information matrix G E Wl r W l r E ee zz r r r r1

77 unitwise metric : Olivier, Kurita 2 G r E erz r1zr1 unitwise metric G diag G, G,, G unit L1 L 1 G diag G,, G r r1 rn

78 Singular Region R w 1 r 1) w w r1 r1 1 2 w 2 w G r1 : singular 2) w 0 G r1 : singular w r

79 W l 0 in R G 1 1 l G l : finite G and G unit

80 High Dimensions 2 e Prob wi wjv1/ n n 2

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

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

Machine Learning. 01 - Introduction

Machine Learning. 01 - Introduction Machine Learning 01 - Introduction Machine learning course One lecture (Wednesday, 9:30, 346) and one exercise (Monday, 17:15, 203). Oral exam, 20 minutes, 5 credit points. Some basic mathematical knowledge

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

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

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

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

Neural Networks: a replacement for Gaussian Processes?

Neural Networks: a replacement for Gaussian Processes? Neural Networks: a replacement for Gaussian Processes? Matthew Lilley and Marcus Frean Victoria University of Wellington, P.O. Box 600, Wellington, New Zealand marcus@mcs.vuw.ac.nz http://www.mcs.vuw.ac.nz/

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

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

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

/SOLUTIONS/ where a, b, c and d are positive constants. Study the stability of the equilibria of this system based on linearization.

/SOLUTIONS/ where a, b, c and d are positive constants. Study the stability of the equilibria of this system based on linearization. echnische Universiteit Eindhoven Faculteit Elektrotechniek NIE-LINEAIRE SYSEMEN / NEURALE NEWERKEN (P6) gehouden op donderdag maart 7, van 9: tot : uur. Dit examenonderdeel bestaat uit 8 opgaven. /SOLUIONS/

More information

Efficient online learning of a non-negative sparse autoencoder

Efficient online learning of a non-negative sparse autoencoder and Machine Learning. Bruges (Belgium), 28-30 April 2010, d-side publi., ISBN 2-93030-10-2. Efficient online learning of a non-negative sparse autoencoder Andre Lemme, R. Felix Reinhart and Jochen J. Steil

More information

Neural Networks for Machine Learning. Lecture 13a The ups and downs of backpropagation

Neural Networks for Machine Learning. Lecture 13a The ups and downs of backpropagation Neural Networks for Machine Learning Lecture 13a The ups and downs of backpropagation Geoffrey Hinton Nitish Srivastava, Kevin Swersky Tijmen Tieleman Abdel-rahman Mohamed A brief history of backpropagation

More information

Introduction to Machine Learning CMU-10701

Introduction to Machine Learning CMU-10701 Introduction to Machine Learning CMU-10701 Deep Learning Barnabás Póczos & Aarti Singh Credits Many of the pictures, results, and other materials are taken from: Ruslan Salakhutdinov Joshua Bengio Geoffrey

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

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

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

Bayesian Machine Learning (ML): Modeling And Inference in Big Data. Zhuhua Cai Google, Rice University caizhua@gmail.com

Bayesian Machine Learning (ML): Modeling And Inference in Big Data. Zhuhua Cai Google, Rice University caizhua@gmail.com Bayesian Machine Learning (ML): Modeling And Inference in Big Data Zhuhua Cai Google Rice University caizhua@gmail.com 1 Syllabus Bayesian ML Concepts (Today) Bayesian ML on MapReduce (Next morning) Bayesian

More information

Design call center management system of e-commerce based on BP neural network and multifractal

Design call center management system of e-commerce based on BP neural network and multifractal Available online www.jocpr.com Journal of Chemical and Pharmaceutical Research, 2014, 6(6):951-956 Research Article ISSN : 0975-7384 CODEN(USA) : JCPRC5 Design call center management system of e-commerce

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

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

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

Accurate and robust image superresolution by neural processing of local image representations

Accurate and robust image superresolution by neural processing of local image representations Accurate and robust image superresolution by neural processing of local image representations Carlos Miravet 1,2 and Francisco B. Rodríguez 1 1 Grupo de Neurocomputación Biológica (GNB), Escuela Politécnica

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

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

Virtual Network Topology Control with Oja and APEX Learning

Virtual Network Topology Control with Oja and APEX Learning Virtual Network Topology Control with Oja and Learning Y. Sinan Hanay, Yuki Koizumi, Shin ichi Arakawa and Masayuki Murata Graduate School of Information Sciences and Technology Osaka University Suita,

More information

An Introduction to Machine Learning

An Introduction to Machine Learning An Introduction to Machine Learning L5: Novelty Detection and Regression Alexander J. Smola Statistical Machine Learning Program Canberra, ACT 0200 Australia Alex.Smola@nicta.com.au Tata Institute, Pune,

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

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

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

Component Ordering in Independent Component Analysis Based on Data Power

Component Ordering in Independent Component Analysis Based on Data Power Component Ordering in Independent Component Analysis Based on Data Power Anne Hendrikse Raymond Veldhuis University of Twente University of Twente Fac. EEMCS, Signals and Systems Group Fac. EEMCS, Signals

More information

Learning is a very general term denoting the way in which agents:

Learning is a very general term denoting the way in which agents: What is learning? Learning is a very general term denoting the way in which agents: Acquire and organize knowledge (by building, modifying and organizing internal representations of some external reality);

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

Activity recognition in ADL settings. Ben Kröse b.j.a.krose@uva.nl

Activity recognition in ADL settings. Ben Kröse b.j.a.krose@uva.nl Activity recognition in ADL settings Ben Kröse b.j.a.krose@uva.nl Content Why sensor monitoring for health and wellbeing? Activity monitoring from simple sensors Cameras Co-design and privacy issues Necessity

More information

Taking Inverse Graphics Seriously

Taking Inverse Graphics Seriously CSC2535: 2013 Advanced Machine Learning Taking Inverse Graphics Seriously Geoffrey Hinton Department of Computer Science University of Toronto The representation used by the neural nets that work best

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

Scalable Machine Learning - or what to do with all that Big Data infrastructure

Scalable Machine Learning - or what to do with all that Big Data infrastructure - or what to do with all that Big Data infrastructure TU Berlin blog.mikiobraun.de Strata+Hadoop World London, 2015 1 Complex Data Analysis at Scale Click-through prediction Personalized Spam Detection

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

Probabilistic Models for Big Data. Alex Davies and Roger Frigola University of Cambridge 13th February 2014

Probabilistic Models for Big Data. Alex Davies and Roger Frigola University of Cambridge 13th February 2014 Probabilistic Models for Big Data Alex Davies and Roger Frigola University of Cambridge 13th February 2014 The State of Big Data Why probabilistic models for Big Data? 1. If you don t have to worry about

More information

Parallel Data Selection Based on Neurodynamic Optimization in the Era of Big Data

Parallel Data Selection Based on Neurodynamic Optimization in the Era of Big Data Parallel Data Selection Based on Neurodynamic Optimization in the Era of Big Data Jun Wang Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Shatin, New Territories,

More information

NTC Project: S01-PH10 (formerly I01-P10) 1 Forecasting Women s Apparel Sales Using Mathematical Modeling

NTC Project: S01-PH10 (formerly I01-P10) 1 Forecasting Women s Apparel Sales Using Mathematical Modeling 1 Forecasting Women s Apparel Sales Using Mathematical Modeling Celia Frank* 1, Balaji Vemulapalli 1, Les M. Sztandera 2, Amar Raheja 3 1 School of Textiles and Materials Technology 2 Computer Information

More information

New Ensemble Combination Scheme

New Ensemble Combination Scheme New Ensemble Combination Scheme Namhyoung Kim, Youngdoo Son, and Jaewook Lee, Member, IEEE Abstract Recently many statistical learning techniques are successfully developed and used in several areas However,

More information

UNIVERSITY OF BOLTON SCHOOL OF ENGINEERING MS SYSTEMS ENGINEERING AND ENGINEERING MANAGEMENT SEMESTER 1 EXAMINATION 2015/2016 INTELLIGENT SYSTEMS

UNIVERSITY OF BOLTON SCHOOL OF ENGINEERING MS SYSTEMS ENGINEERING AND ENGINEERING MANAGEMENT SEMESTER 1 EXAMINATION 2015/2016 INTELLIGENT SYSTEMS TW72 UNIVERSITY OF BOLTON SCHOOL OF ENGINEERING MS SYSTEMS ENGINEERING AND ENGINEERING MANAGEMENT SEMESTER 1 EXAMINATION 2015/2016 INTELLIGENT SYSTEMS MODULE NO: EEM7010 Date: Monday 11 th January 2016

More information

University of Cambridge Engineering Part IIB Module 4F10: Statistical Pattern Processing Handout 8: Multi-Layer Perceptrons

University of Cambridge Engineering Part IIB Module 4F10: Statistical Pattern Processing Handout 8: Multi-Layer Perceptrons University of Cambridge Engineering Part IIB Module 4F0: Statistical Pattern Processing Handout 8: Multi-Layer Perceptrons x y (x) Inputs x 2 y (x) 2 Outputs x d First layer Second Output layer layer y

More information

Manifold Learning with Variational Auto-encoder for Medical Image Analysis

Manifold Learning with Variational Auto-encoder for Medical Image Analysis Manifold Learning with Variational Auto-encoder for Medical Image Analysis Eunbyung Park Department of Computer Science University of North Carolina at Chapel Hill eunbyung@cs.unc.edu Abstract Manifold

More information

Optimizing content delivery through machine learning. James Schneider Anton DeFrancesco

Optimizing content delivery through machine learning. James Schneider Anton DeFrancesco Optimizing content delivery through machine learning James Schneider Anton DeFrancesco Obligatory company slide Our Research Areas Machine learning The problem Prioritize import information in low bandwidth

More information

Computer Science MS Course Descriptions

Computer Science MS Course Descriptions Computer Science MS Course Descriptions CSc I0400: Operating Systems Underlying theoretical structure of operating systems; input-output and storage systems, data management and processing; assembly and

More information

Section for Cognitive Systems DTU Informatics, Technical University of Denmark

Section for Cognitive Systems DTU Informatics, Technical University of Denmark Transformation Invariant Sparse Coding Morten Mørup & Mikkel N Schmidt Morten Mørup & Mikkel N. Schmidt Section for Cognitive Systems DTU Informatics, Technical University of Denmark Redundancy Reduction

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

3. Reaction Diffusion Equations Consider the following ODE model for population growth

3. Reaction Diffusion Equations Consider the following ODE model for population growth 3. Reaction Diffusion Equations Consider the following ODE model for population growth u t a u t u t, u 0 u 0 where u t denotes the population size at time t, and a u plays the role of the population dependent

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

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

Topological Data Analysis Applications to Computer Vision

Topological Data Analysis Applications to Computer Vision Topological Data Analysis Applications to Computer Vision Vitaliy Kurlin, http://kurlin.org Microsoft Research Cambridge and Durham University, UK Topological Data Analysis quantifies topological structures

More information

Natural Conjugate Gradient in Variational Inference

Natural Conjugate Gradient in Variational Inference Natural Conjugate Gradient in Variational Inference Antti Honkela, Matti Tornio, Tapani Raiko, and Juha Karhunen Adaptive Informatics Research Centre, Helsinki University of Technology P.O. Box 5400, FI-02015

More information

Sense Making in an IOT World: Sensor Data Analysis with Deep Learning

Sense Making in an IOT World: Sensor Data Analysis with Deep Learning Sense Making in an IOT World: Sensor Data Analysis with Deep Learning Natalia Vassilieva, PhD Senior Research Manager GTC 2016 Deep learning proof points as of today Vision Speech Text Other Search & information

More information

A Content based Spam Filtering Using Optical Back Propagation Technique

A Content based Spam Filtering Using Optical Back Propagation Technique A Content based Spam Filtering Using Optical Back Propagation Technique Sarab M. Hameed 1, Noor Alhuda J. Mohammed 2 Department of Computer Science, College of Science, University of Baghdad - Iraq ABSTRACT

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

Course: Model, Learning, and Inference: Lecture 5

Course: Model, Learning, and Inference: Lecture 5 Course: Model, Learning, and Inference: Lecture 5 Alan Yuille Department of Statistics, UCLA Los Angeles, CA 90095 yuille@stat.ucla.edu Abstract Probability distributions on structured representation.

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

Probabilistic Linear Classification: Logistic Regression. Piyush Rai IIT Kanpur

Probabilistic Linear Classification: Logistic Regression. Piyush Rai IIT Kanpur Probabilistic Linear Classification: Logistic Regression Piyush Rai IIT Kanpur Probabilistic Machine Learning (CS772A) Jan 18, 2016 Probabilistic Machine Learning (CS772A) Probabilistic Linear Classification:

More information

3. Regression & Exponential Smoothing

3. Regression & Exponential Smoothing 3. Regression & Exponential Smoothing 3.1 Forecasting a Single Time Series Two main approaches are traditionally used to model a single time series z 1, z 2,..., z n 1. Models the observation z t as a

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

129: Artificial Neural Networks. Ajith Abraham Oklahoma State University, Stillwater, OK, USA 1 INTRODUCTION TO ARTIFICIAL NEURAL NETWORKS

129: Artificial Neural Networks. Ajith Abraham Oklahoma State University, Stillwater, OK, USA 1 INTRODUCTION TO ARTIFICIAL NEURAL NETWORKS 129: Artificial Neural Networks Ajith Abraham Oklahoma State University, Stillwater, OK, USA 1 Introduction to Artificial Neural Networks 901 2 Neural Network Architectures 902 3 Neural Network Learning

More information

2.2 Creaseness operator

2.2 Creaseness operator 2.2. Creaseness operator 31 2.2 Creaseness operator Antonio López, a member of our group, has studied for his PhD dissertation the differential operators described in this section [72]. He has compared

More information

Models of Cortical Maps II

Models of Cortical Maps II CN510: Principles and Methods of Cognitive and Neural Modeling Models of Cortical Maps II Lecture 19 Instructor: Anatoli Gorchetchnikov dy dt The Network of Grossberg (1976) Ay B y f (

More information

Application of Neural Network in User Authentication for Smart Home System

Application of Neural Network in User Authentication for Smart Home System Application of Neural Network in User Authentication for Smart Home System A. Joseph, D.B.L. Bong, D.A.A. Mat Abstract Security has been an important issue and concern in the smart home systems. Smart

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

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

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

KATE GLEASON COLLEGE OF ENGINEERING. John D. Hromi Center for Quality and Applied Statistics

KATE GLEASON COLLEGE OF ENGINEERING. John D. Hromi Center for Quality and Applied Statistics ROCHESTER INSTITUTE OF TECHNOLOGY COURSE OUTLINE FORM KATE GLEASON COLLEGE OF ENGINEERING John D. Hromi Center for Quality and Applied Statistics NEW (or REVISED) COURSE (KGCOE- CQAS- 747- Principles of

More information

MANAGING QUEUE STABILITY USING ART2 IN ACTIVE QUEUE MANAGEMENT FOR CONGESTION CONTROL

MANAGING QUEUE STABILITY USING ART2 IN ACTIVE QUEUE MANAGEMENT FOR CONGESTION CONTROL MANAGING QUEUE STABILITY USING ART2 IN ACTIVE QUEUE MANAGEMENT FOR CONGESTION CONTROL G. Maria Priscilla 1 and C. P. Sumathi 2 1 S.N.R. Sons College (Autonomous), Coimbatore, India 2 SDNB Vaishnav College

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

Machine learning challenges for big data

Machine learning challenges for big data Machine learning challenges for big data Francis Bach SIERRA Project-team, INRIA - Ecole Normale Supérieure Joint work with R. Jenatton, J. Mairal, G. Obozinski, N. Le Roux, M. Schmidt - December 2012

More information

Feature Engineering in Machine Learning

Feature Engineering in Machine Learning Research Fellow Faculty of Information Technology, Monash University, Melbourne VIC 3800, Australia August 21, 2015 Outline A Machine Learning Primer Machine Learning and Data Science Bias-Variance Phenomenon

More information

Neural Network Add-in

Neural Network Add-in Neural Network Add-in Version 1.5 Software User s Guide Contents Overview... 2 Getting Started... 2 Working with Datasets... 2 Open a Dataset... 3 Save a Dataset... 3 Data Pre-processing... 3 Lagging...

More information

SMORN-VII REPORT NEURAL NETWORK BENCHMARK ANALYSIS RESULTS & FOLLOW-UP 96. Özer CIFTCIOGLU Istanbul Technical University, ITU. and

SMORN-VII REPORT NEURAL NETWORK BENCHMARK ANALYSIS RESULTS & FOLLOW-UP 96. Özer CIFTCIOGLU Istanbul Technical University, ITU. and NEA/NSC-DOC (96)29 AUGUST 1996 SMORN-VII REPORT NEURAL NETWORK BENCHMARK ANALYSIS RESULTS & FOLLOW-UP 96 Özer CIFTCIOGLU Istanbul Technical University, ITU and Erdinç TÜRKCAN Netherlands Energy Research

More information

Linear Classification. Volker Tresp Summer 2015

Linear Classification. Volker Tresp Summer 2015 Linear Classification Volker Tresp Summer 2015 1 Classification Classification is the central task of pattern recognition Sensors supply information about an object: to which class do the object belong

More information

ARTIFICIAL INTELLIGENCE METHODS IN EARLY MANUFACTURING TIME ESTIMATION

ARTIFICIAL INTELLIGENCE METHODS IN EARLY MANUFACTURING TIME ESTIMATION 1 ARTIFICIAL INTELLIGENCE METHODS IN EARLY MANUFACTURING TIME ESTIMATION B. Mikó PhD, Z-Form Tool Manufacturing and Application Ltd H-1082. Budapest, Asztalos S. u 4. Tel: (1) 477 1016, e-mail: miko@manuf.bme.hu

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

Dirichlet forms methods for error calculus and sensitivity analysis

Dirichlet forms methods for error calculus and sensitivity analysis Dirichlet forms methods for error calculus and sensitivity analysis Nicolas BOULEAU, Osaka university, november 2004 These lectures propose tools for studying sensitivity of models to scalar or functional

More information

Dimension Theory for Ordinary Differential Equations

Dimension Theory for Ordinary Differential Equations Vladimir A. Boichenko, Gennadij A. Leonov, Volker Reitmann Dimension Theory for Ordinary Differential Equations Teubner Contents Singular values, exterior calculus and Lozinskii-norms 15 1 Singular values

More information

Monotonicity Hints. Abstract

Monotonicity Hints. Abstract Monotonicity Hints Joseph Sill Computation and Neural Systems program California Institute of Technology email: joe@cs.caltech.edu Yaser S. Abu-Mostafa EE and CS Deptartments California Institute of Technology

More information

Exact Inference for Gaussian Process Regression in case of Big Data with the Cartesian Product Structure

Exact Inference for Gaussian Process Regression in case of Big Data with the Cartesian Product Structure Exact Inference for Gaussian Process Regression in case of Big Data with the Cartesian Product Structure Belyaev Mikhail 1,2,3, Burnaev Evgeny 1,2,3, Kapushev Yermek 1,2 1 Institute for Information Transmission

More information

Università degli Studi di Bologna

Università degli Studi di Bologna Università degli Studi di Bologna DEIS Biometric System Laboratory Incremental Learning by Message Passing in Hierarchical Temporal Memory Davide Maltoni Biometric System Laboratory DEIS - University of

More information

Appendix 4 Simulation software for neuronal network models

Appendix 4 Simulation software for neuronal network models Appendix 4 Simulation software for neuronal network models D.1 Introduction This Appendix describes the Matlab software that has been made available with Cerebral Cortex: Principles of Operation (Rolls

More information

Unknown n sensors x(t)

Unknown n sensors x(t) Appeared in journal: Neural Network World Vol.6, No.4, 1996, pp.515{523. Published by: IDG Co., Prague, Czech Republic. LOCAL ADAPTIVE LEARNING ALGORITHMS FOR BLIND SEPARATION OF NATURAL IMAGES Andrzej

More information

Machine Learning for Data Science (CS4786) Lecture 1

Machine Learning for Data Science (CS4786) Lecture 1 Machine Learning for Data Science (CS4786) Lecture 1 Tu-Th 10:10 to 11:25 AM Hollister B14 Instructors : Lillian Lee and Karthik Sridharan ROUGH DETAILS ABOUT THE COURSE Diagnostic assignment 0 is out:

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

Introduction to Probability

Introduction to Probability Introduction to Probability EE 179, Lecture 15, Handout #24 Probability theory gives a mathematical characterization for experiments with random outcomes. coin toss life of lightbulb binary data sequence

More information

CSCI567 Machine Learning (Fall 2014)

CSCI567 Machine Learning (Fall 2014) CSCI567 Machine Learning (Fall 2014) Drs. Sha & Liu {feisha,yanliu.cs}@usc.edu September 22, 2014 Drs. Sha & Liu ({feisha,yanliu.cs}@usc.edu) CSCI567 Machine Learning (Fall 2014) September 22, 2014 1 /

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

Lecture 2: The SVM classifier

Lecture 2: The SVM classifier Lecture 2: The SVM classifier C19 Machine Learning Hilary 2015 A. Zisserman Review of linear classifiers Linear separability Perceptron Support Vector Machine (SVM) classifier Wide margin Cost function

More information

Adaptive Control Using Combined Online and Background Learning Neural Network

Adaptive Control Using Combined Online and Background Learning Neural Network Adaptive Control Using Combined Online and Background Learning Neural Network Eric N. Johnson and Seung-Min Oh Abstract A new adaptive neural network (NN control concept is proposed with proof of stability

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

Section 5. Stan for Big Data. Bob Carpenter. Columbia University

Section 5. Stan for Big Data. Bob Carpenter. Columbia University Section 5. Stan for Big Data Bob Carpenter Columbia University Part I Overview Scaling and Evaluation data size (bytes) 1e18 1e15 1e12 1e9 1e6 Big Model and Big Data approach state of the art big model

More information

COMBINED NEURAL NETWORKS FOR TIME SERIES ANALYSIS

COMBINED NEURAL NETWORKS FOR TIME SERIES ANALYSIS COMBINED NEURAL NETWORKS FOR TIME SERIES ANALYSIS Iris Ginzburg and David Horn School of Physics and Astronomy Raymond and Beverly Sackler Faculty of Exact Science Tel-Aviv University Tel-A viv 96678,

More information

Coding and decoding with convolutional codes. The Viterbi Algor

Coding and decoding with convolutional codes. The Viterbi Algor Coding and decoding with convolutional codes. The Viterbi Algorithm. 8 Block codes: main ideas Principles st point of view: infinite length block code nd point of view: convolutions Some examples Repetition

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

Lecture 9: Introduction to Pattern Analysis

Lecture 9: Introduction to Pattern Analysis Lecture 9: Introduction to Pattern Analysis g Features, patterns and classifiers g Components of a PR system g An example g Probability definitions g Bayes Theorem g Gaussian densities Features, patterns

More information