HE Shuncheng March 20, 2016
|
|
- Zoe Todd
- 7 years ago
- Views:
Transcription
1 Department of Automation Association of Science and Technology of Automation March 20, 2016
2 Contents
3
4 Binary Figure 1: a cat? Figure 2: a dog? Binary : Given input data x (e.g. a picture), the output of a binary classifier y = f (x) is one label retrieved from a set of two labels y {±1}.
5 Linear Classifier x w T x = b x 1 Data set D = {(x (1) 1, x (1) (n) 2 ),, (x 1, x (n) 2 )} A linear binary classifier is a hyperplane w T x = b f (x) = sgn(w T x b)
6 of Linear Classifier + + x w T x = b x 1 True Positive: y = +1, f (x) = +1 True Negative: y = 1, f (x) = 1 False Positive: y = 1, f (x) = +1 False Negative: y = +1, f (x) = 1 Accuracy: TP+TN n Error Rate: FP+FN n A good classifier: minizing the error rate
7 Basic Concepts x x 1 Training Set Test Set Training Error Generalization Error Overfitting Loss Function w T x = b training error training data classifier output loss function
8 Overfitting + + x 2 + error rate generalization error x 1 training error iteration
9
10 Perceptron x 0 = 1 x 1 x 2 w 1 w 2 w 0 y x n w n n i=0 w ix i { +1, if w T x > 0 y = 1, otherwise
11 Perceptron x 1 x 2 w 1 w 2 x 0 = 1 w 0 o(x 0, x 1,, x n ) = n i=0 w ix i n i=0 w o ix i w n x n
12 Training Algorithm Define a loss function: How to reduce loss? E(w) = 1 (t d o d ) 2 2 d D y x 2
13 Gradient Descent Gradient w.r.t. w where E(w) = ( E w 0, E w 1,, E w n ) T E = (t d o d )( x (d) i ) w i d D for every iteration (α denotes learning rate) w i w i + w i w i = α E = α (t d o d )x (d) i w i d D i [n]
14 Artificial input layer x (1) 1 x (1) 2 hidden layer x (2) 1 x (2) 2 x (2) 3 output layer x (3) 1 h is a non-linear function. x l+1 = h((w l ) T x l )
15 Sigmoid Function h(x) = h(x) e x 0 1. continuous, differentiable 2. map [, + ] to [0, 1] 3. nonlinearity 4. h (x) is easy to calculate h (x) = h(x)(1 h(x)) x
16 Back Propagation and Delta Rule Please refer to this page Mathematical model of ANN x l = f (u l ), u l = (W l 1 ) T x l 1 where l denotes the current layer with the output layer designated to be layer L and the input layer desiganted to ba layer 1. Function f ( ) is a nonlinear function (i.e. sigmoid or hyperbolic tangent). Define loss function as E(x L, t) where x L is the network output and t is the target output.
17 Back Propagation and Delta Rule Expand the loss function E(x L, t) = E(f ((W L 1 ) T x L 1 ), t) Using chain rule, we can write the derivatives w.r.t. W L 1 E W L 1 = x L 1 (f (u L ) E x L )T where denotes elementwise multiplication, and if we define we get δ L = f (u L ) E x L E W L 1 = x L 1 (δ L ) T
18 Back Propagation and Delta Rule If we calculate the δ term recursively it is easy to write δ l = f (u l ) ((W l ) T δ l+1 ), l = L 1,, 2 E W l = x l (δ l+1 ) T, l = L 2,, 1
19
20 Network Structure Figure 3: structure of convolutional neural network Convolution Layer Pooling Layer (Subsampling) Full-connected Layer (Inner-product) ReLU Layer Softmax Layer
21 Convolution Layer kernel size=3 3 j+2 i+2 g ij = h st k st s=i t=j
22 Convolution Layer stride=1 j+2 i+2 g ij = h st k st s=i t=j
23 Convolution Layer Why we choose convolution? Inspired from feature extraction - using different kernels On the assumption that pixels far from each other are independent Reducing adjustable network weights to avoid overfitting
24 Pooling Layer g ij = max{h 2i,2j, h 2i+1,2j, h 2i,2j+1, h 2i+1,2j+1 } No free parameter in pooling layer.
25 Pooling Layer g ij = max{h 2i,2j, h 2i+1,2j, h 2i,2j+1, h 2i+1,2j+1 } No free parameter in pooling layer.
26 Inner-product Known as full-connected layer. Weights are designated from every input to every output, namely y = W T x
27 Rectified Linear Unit A rectifier y = max{0, x} A rectified linear unit y = ln(1 + e x ) with its derivative w.r.t. x dy dx = e x y x ReLU improves CNN performance.
28 Softmax Loss Softmax: y i (x) = e x i n, i [n] k=1 ex k Derived from softmax regression, extension of logistic regression for multinomial classfication. Outputs of softmax layer are probabilities of each label. Softmax loss function: let label j be groundtruth, therefore e x j n L = ln(y j (x)) = ln( n ) = ln( e x k ) x j k=1 ex k k=1 L x i = y i (x) δ ij where δ ij = 1 iff i = j, and δ ij = 0 otherwise.
29 MNIST Database MNIST: Mixed National Institute of Standards and Technology Figure 4: Handwritten Digits 10 distinguishing classes
30 LeNet Review Figure 5: LeNet for MNIST input: a picture (size 28 28) conv1: 4 kernels (size 5 5) pool1: max pooling (size 2 2) conv2: 3 kernels (size 5 5) pool2: max pooling (size 2 2) ip: full-connected (192 10) softmax: 10 inputs, 10 prob outputs
31
32 Stochastic gradient descent Early stop Weight decay Rectified linear unit Finetune Overlapping pooling Dropout
33 Stochastic Gradient Descent Overall loss function: Batch loss function: E(w) = 1 (t d o d ) 2 2 d D E B (w) = 1 (t d o d ) 2 2 d B where B D and B D, e.g. 256 samples out of samples. Stochastic gradient: E B w
34 Stochastic Gradient Descent SGD algorithm: α: learning rate µ: momentum Advantages of SGD: w t+1 = w t + w t w t+1 = µ w t α L w t Reducing computing resources dramatically Escaping local optimal solutions
35 Early Stop error rate stop training generalization error training error iteration Stop before generalization error rises
36 Weight Decay Regularization: In algorithm: E(w) = 1 (t d o d ) 2 + λw T W 2 d D w t+1 = µ w t α L w t αλw t
37 Rectified Linear Unit y x In terms of training time with gradient descent, saturating nonlinearities such as sigmoid and tanh are much slower than non-saturating nonlinearities.
38 Dropout Overfitting can be reduced by using dropout to prevent complex co-adaptations on the training data. On each presentation of each training case, each hidden unit is randomly omitted from the network with a probability of 0.5, so a hidden unit cannot rely on other hidden units being present.
39
40 Network in Network Network in network is a new concept in GoogLeNet, the champion of ILSVRC (ImageNet Large Scale Visual Recognition Challenge) The key structure of network in network is called Inception module. The whole network structure.
41 Network in Network Motivations to choose this structure: Deeper network tend to have stronger learning ability - especially handling with large scale datasets Dimension Curse in neural network - exponential expansion of parameters Very sparse deep neural network can be constructed layer by layer by analyzing the correlation statistics Inception module is a try to approximate a sparse structure Details about inception module: Various scale of convolution is necessary for small or big features - inspired from Gabor filter 1 1 convolution is used to reduce dimension
42 Network in Network The result of ILSVRC 2014:
43 Residual Network Encountering degradation problem when network is going deeper:
44 Residual Network An intuitive solution to construct a deep model from a shallow model: shallow model identity map identity map m layers n layers (n m) Unable to reach a better solution than the original model.
45 Residual Network Learning a residual (F(x) = H(x) x): Finally reached the depth of up to 152 layers.
46 Residual Network The result of ILSVRC 2015:
47 BNN: Binarized s Deterministic or stochastic binarization: { x b +1 if x 0, = sgn(x) = 1 otherwise. x b = { +1 with probability p = σ(x), 1 with probability 1 p. 1 σ(x) O -1 1 x
48 BNN: Binarized s Binarized conv kernel: Only 42% of the filters are unique on CIFAR-10 ConvNet.
49 BNN: Binarized s : 1. As accurate as 32-bit DNNs
50 BNN: Binarized s : 2. Less computional consumption
51 CNN Visualization Use deconvolutional network to visualize higher layer s feature map. Three keypoints are mentioned: Unpooling: approximate inverse of max pooling by recording the location of maxima Rectification: pass reconstructed signals through ReLU Filtering: use transposed version of the same filters
52 CNN Visualization Different results of visualization: Feature map in each layers Evolution of features
53 More Tremendous Development Long Short-Term Memory (LSTM) Region-based CNN (R-CNN, fast R-CNN, faster R-CNN) Deep Belief Networks (Restricted Boltzmann Machine) AlphaGo and Reinforment Learning CNN for Speech Recognition
54
55 Caffe Tutorial For more information please refer to this page. Key words: Nets, Layers and Blobs Forward / Backward Loss Solver Layer Catalogue Interfaces Data
56 Nets, Layers and Blobs Layer Net Blob : Softmax Regression
57 Forward / Backward f (w T x) L(f (w T x)) w T x L f L w x
58 Loss Softmax: y i (x) = e x i n, i [n] k=1 ex k Softmax loss function: let label j be groundtruth, therefore e x j n L = ln(y j (x)) = ln( n ) = ln( e x k ) x j k=1 ex k L x i = y i (x) δ ij where δ ij = 1 iff i = j, and δ ij = 0 otherwise. k=1
59 Solver SGD (Stochastic Gradient Descent) α: learning rate µ: momentum w t+1 = w t + w t w t+1 = µ w t α L w t
60 Solver Solver parameters (i.e.): basic learning rate: α = 0.01 learning rate policy: step (reduce learning rate according to step size) step size: gamma: 0.1 (multipy learning rate with factor 0.1 after step size) momentum: µ = 0.9 max iteration: (stop at iteration )
61 Layer Catalogue Please refer to this page. Vision layer: convolution pooling Loss layer: softmax loss Euclidean loss cross-entropy Activation layer: sigmoid ReLU hyperbolic tangent
62 Layer Catalogue Data layer: datebase in-memory HDF5 input HDF5 output Common layer: inner product splitting flatening reshape concatenation
63
64 Installation Prerequisites: protobuf, CUDA, OpenBLAS, Boost, OpenCV, lmdb, leveldb, cudnn(optional), Python(optional), numpy(optional), MATLAB(optional) Install: git clone git://github.com/bvlc/caffe /your/own/caffe/folder Go to Caffe root folder cp Makefile.config.example Makefile.config make all make test make runtest Hardware: K40, K20, Titan for ImageNet scale GTX series or GPU-equipped MacBook Pro for small datasets
65 LeNet LeNet Structure 1. Protobuf Protocol 2. Run!
66 How to be Professional? 1. Figure out theoretical keypoints (read papers) 2. Read Caffe source code 3. Be proficient at programming and debugging skills 4. Take advantage of search engine and community 5. Do it through this pipeline: Experiment design Data preparation (build database with tools) Model selection (including network and solver) Training Analysis and comparison
67 Reference I Ossama Abdel-Hamid, Li Deng, and Dong Yu. Exploring convolutional neural network structures and optimization techniques for speech recognition. In INTERSPEECH, pages , Christopher M Bishop. Pattern recognition. Machine Learning, Ross Girshick. Fast r-cnn. In Proceedings of the IEEE International Conference on Computer Vision, pages , Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. arxiv preprint arxiv: , 2015.
68 Reference II Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9(8): , Itay Hubara, Daniel Soudry, and Ran El Yaniv. Binarized neural networks. arxiv preprint arxiv: , Herbert Jaeger. Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the echo state network approach. GMD-Forschungszentrum Informationstechnik, 2002.
69 Reference III Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell. Caffe: architecture for fast feature embedding. In Proceedings of the ACM International Conference on Multimedia, pages ACM, Abdel-rahman Mohamed, George E Dahl, and Geoffrey Hinton. Acoustic modeling using deep belief networks. Audio, Speech, and Language Processing, IEEE Transactions on, 20(1):14 22, 2012.
70 Reference IV Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in Neural Information Processing Systems, pages 91 99, David Silver, Aja Huang, Chris J Maddison, Arthur Guez, Laurent Sifre, George van den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et al. Mastering the game of go with deep neural networks and tree search. Nature, 529(7587): , 2016.
71 Reference V Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1 9, Matthew D Zeiler and Rob Fergus. Visualizing and understanding convolutional networks. In Computer vision ECCV 2014, pages Springer, 2014.
Convolutional Feature Maps
Convolutional Feature Maps Elements of efficient (and accurate) CNN-based object detection Kaiming He Microsoft Research Asia (MSRA) ICCV 2015 Tutorial on Tools for Efficient Object Detection Overview
More informationCS 1699: Intro to Computer Vision. Deep Learning. Prof. Adriana Kovashka University of Pittsburgh December 1, 2015
CS 1699: Intro to Computer Vision Deep Learning Prof. Adriana Kovashka University of Pittsburgh December 1, 2015 Today: Deep neural networks Background Architectures and basic operations Applications Visualizing
More informationImage and Video Understanding
Image and Video Understanding 2VO 710.095 WS Christoph Feichtenhofer, Axel Pinz Slide credits: Many thanks to all the great computer vision researchers on which this presentation relies on. Most material
More informationBert Huang Department of Computer Science Virginia Tech
This paper was submitted as a final project report for CS6424/ECE6424 Probabilistic Graphical Models and Structured Prediction in the spring semester of 2016. The work presented here is done by students
More informationDenoising Convolutional Autoencoders for Noisy Speech Recognition
Denoising Convolutional Autoencoders for Noisy Speech Recognition Mike Kayser Stanford University mkayser@stanford.edu Victor Zhong Stanford University vzhong@stanford.edu Abstract We propose the use of
More informationFast R-CNN Object detection with Caffe
Fast R-CNN Object detection with Caffe Ross Girshick Microsoft Research arxiv code Latest roasts Goals for this section Super quick intro to object detection Show one way to tackle obj. det. with ConvNets
More informationLecture 6: Classification & Localization. boris. ginzburg@intel.com
Lecture 6: Classification & Localization boris. ginzburg@intel.com 1 Agenda ILSVRC 2014 Overfeat: integrated classification, localization, and detection Classification with Localization Detection. 2 ILSVRC-2014
More informationIntroduction 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 informationGetting Started with Caffe Julien Demouth, Senior Engineer
Getting Started with Caffe Julien Demouth, Senior Engineer What is Caffe? Open Source Framework for Deep Learning http://github.com/bvlc/caffe Developed by the Berkeley Vision and Learning Center (BVLC)
More informationCompacting ConvNets for end to end Learning
Compacting ConvNets for end to end Learning Jose M. Alvarez Joint work with Lars Pertersson, Hao Zhou, Fatih Porikli. Success of CNN Image Classification Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton,
More informationSteven C.H. Hoi School of Information Systems Singapore Management University Email: chhoi@smu.edu.sg
Steven C.H. Hoi School of Information Systems Singapore Management University Email: chhoi@smu.edu.sg Introduction http://stevenhoi.org/ Finance Recommender Systems Cyber Security Machine Learning Visual
More informationLearning 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 informationLecture 6: CNNs for Detection, Tracking, and Segmentation Object Detection
CSED703R: Deep Learning for Visual Recognition (206S) Lecture 6: CNNs for Detection, Tracking, and Segmentation Object Detection Bohyung Han Computer Vision Lab. bhhan@postech.ac.kr 2 3 Object detection
More informationModule 5. Deep Convnets for Local Recognition Joost van de Weijer 4 April 2016
Module 5 Deep Convnets for Local Recognition Joost van de Weijer 4 April 2016 Previously, end-to-end.. Dog Slide credit: Jose M 2 Previously, end-to-end.. Dog Learned Representation Slide credit: Jose
More informationNetwork Morphism. Abstract. 1. Introduction. Tao Wei
Tao Wei TAOWEI@BUFFALO.EDU Changhu Wang CHW@MICROSOFT.COM Yong Rui YONGRUI@MICROSOFT.COM Chang Wen Chen CHENCW@BUFFALO.EDU Microsoft Research, Beijing, China, 18 Department of Computer Science and Engineering,
More informationPedestrian Detection with RCNN
Pedestrian Detection with RCNN Matthew Chen Department of Computer Science Stanford University mcc17@stanford.edu Abstract In this paper we evaluate the effectiveness of using a Region-based Convolutional
More informationStochastic Pooling for Regularization of Deep Convolutional Neural Networks
Stochastic Pooling for Regularization of Deep Convolutional Neural Networks Matthew D. Zeiler Department of Computer Science Courant Institute, New York University zeiler@cs.nyu.edu Rob Fergus Department
More informationA Dynamic Convolutional Layer for Short Range Weather Prediction
A Dynamic Convolutional Layer for Short Range Weather Prediction Benjamin Klein, Lior Wolf and Yehuda Afek The Blavatnik School of Computer Science Tel Aviv University beni.klein@gmail.com, wolf@cs.tau.ac.il,
More informationImage Classification for Dogs and Cats
Image Classification for Dogs and Cats Bang Liu, Yan Liu Department of Electrical and Computer Engineering {bang3,yan10}@ualberta.ca Kai Zhou Department of Computing Science kzhou3@ualberta.ca Abstract
More informationAdministrivia. Traditional Recognition Approach. Overview. CMPSCI 370: Intro. to Computer Vision Deep learning
: Intro. to Computer Vision Deep learning University of Massachusetts, Amherst April 19/21, 2016 Instructor: Subhransu Maji Finals (everyone) Thursday, May 5, 1-3pm, Hasbrouck 113 Final exam Tuesday, May
More informationFast R-CNN. Author: Ross Girshick Speaker: Charlie Liu Date: Oct, 13 th. Girshick, R. (2015). Fast R-CNN. arxiv preprint arxiv:1504.08083.
Fast R-CNN Author: Ross Girshick Speaker: Charlie Liu Date: Oct, 13 th Girshick, R. (2015). Fast R-CNN. arxiv preprint arxiv:1504.08083. ECS 289G 001 Paper Presentation, Prof. Lee Result 1 67% Accuracy
More informationDeep Residual Networks
Deep Residual Networks Deep Learning Gets Way Deeper 8:30-10:30am, June 19 ICML 2016 tutorial Kaiming He Facebook AI Research* *as of July 2016. Formerly affiliated with Microsoft Research Asia 7x7 conv,
More informationCAP 6412 Advanced Computer Vision
CAP 6412 Advanced Computer Vision http://www.cs.ucf.edu/~bgong/cap6412.html Boqing Gong Jan 26, 2016 Today Administrivia A bigger picture and some common questions Object detection proposals, by Samer
More informationSupporting Online Material for
www.sciencemag.org/cgi/content/full/313/5786/504/dc1 Supporting Online Material for Reducing the Dimensionality of Data with Neural Networks G. E. Hinton* and R. R. Salakhutdinov *To whom correspondence
More informationarxiv:1502.01852v1 [cs.cv] 6 Feb 2015
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification Kaiming He Xiangyu Zhang Shaoqing Ren Jian Sun arxiv:1502.01852v1 [cs.cv] 6 Feb 2015 Abstract Rectified activation
More informationSequence to Sequence Weather Forecasting with Long Short-Term Memory Recurrent Neural Networks
Volume 143 - No.11, June 16 Sequence to Sequence Weather Forecasting with Long Short-Term Memory Recurrent Neural Networks Mohamed Akram Zaytar Research Student Department of Computer Engineering Faculty
More informationPedestrian Detection using R-CNN
Pedestrian Detection using R-CNN CS676A: Computer Vision Project Report Advisor: Prof. Vinay P. Namboodiri Deepak Kumar Mohit Singh Solanki (12228) (12419) Group-17 April 15, 2016 Abstract Pedestrian detection
More informationConvolutional Networks for Stock Trading
Convolutional Networks for Stock Trading Ashwin Siripurapu Stanford University Department of Computer Science 353 Serra Mall, Stanford, CA 94305 ashwin@cs.stanford.edu Abstract Convolutional neural networks
More informationDo Deep Nets Really Need to be Deep?
Do Deep Nets Really Need to be Deep? Lei Jimmy Ba University of Toronto jimmy@psi.utoronto.ca Rich Caruana Microsoft Research rcaruana@microsoft.com Abstract Currently, deep neural networks are the state
More informationAdvanced 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 informationLecture 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 informationSimplified Machine Learning for CUDA. Umar Arshad @arshad_umar Arrayfire @arrayfire
Simplified Machine Learning for CUDA Umar Arshad @arshad_umar Arrayfire @arrayfire ArrayFire CUDA and OpenCL experts since 2007 Headquartered in Atlanta, GA In search for the best and the brightest Expert
More informationDeep Learning using Linear Support Vector Machines
Yichuan Tang tang@cs.toronto.edu Department of Computer Science, University of Toronto. Toronto, Ontario, Canada. Abstract Recently, fully-connected and convolutional neural networks have been trained
More informationDeformable Part Models with CNN Features
Deformable Part Models with CNN Features Pierre-André Savalle 1, Stavros Tsogkas 1,2, George Papandreou 3, Iasonas Kokkinos 1,2 1 Ecole Centrale Paris, 2 INRIA, 3 TTI-Chicago Abstract. In this work we
More informationArtificial 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 informationNEURAL 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 informationInstaNet: Object Classification Applied to Instagram Image Streams
InstaNet: Object Classification Applied to Instagram Image Streams Clifford Huang Stanford University chuang8@stanford.edu Mikhail Sushkov Stanford University msushkov@stanford.edu Abstract The growing
More informationCNN Based Object Detection in Large Video Images. WangTao, wtao@qiyi.com IQIYI ltd. 2016.4
CNN Based Object Detection in Large Video Images WangTao, wtao@qiyi.com IQIYI ltd. 2016.4 Outline Introduction Background Challenge Our approach System framework Object detection Scene recognition Body
More informationNovelty 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 informationMulticoreWare. Global Company, 250+ employees HQ = Sunnyvale, CA Other locations: US, China, India, Taiwan
1 MulticoreWare Global Company, 250+ employees HQ = Sunnyvale, CA Other locations: US, China, India, Taiwan Focused on Heterogeneous Computing Multiple verticals spawned from core competency Machine Learning
More informationSIGNAL INTERPRETATION
SIGNAL INTERPRETATION Lecture 6: ConvNets February 11, 2016 Heikki Huttunen heikki.huttunen@tut.fi Department of Signal Processing Tampere University of Technology CONVNETS Continued from previous slideset
More informationEfficient 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 informationMachine 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 informationAn Early Attempt at Applying Deep Reinforcement Learning to the Game 2048
An Early Attempt at Applying Deep Reinforcement Learning to the Game 2048 Hong Gui, Tinghan Wei, Ching-Bo Huang, I-Chen Wu 1 1 Department of Computer Science, National Chiao Tung University, Hsinchu, Taiwan
More informationImageNet Classification with Deep Convolutional Neural Networks
ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky University of Toronto kriz@cs.utoronto.ca Ilya Sutskever University of Toronto ilya@cs.utoronto.ca Geoffrey E. Hinton University
More informationMulti-view Face Detection Using Deep Convolutional Neural Networks
Multi-view Face Detection Using Deep Convolutional Neural Networks Sachin Sudhakar Farfade Yahoo fsachin@yahoo-inc.com Mohammad Saberian Yahoo saberian@yahooinc.com Li-Jia Li Yahoo lijiali@cs.stanford.edu
More informationUniversity 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 informationarxiv:1506.03365v2 [cs.cv] 19 Jun 2015
LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop Fisher Yu Yinda Zhang Shuran Song Ari Seff Jianxiong Xiao arxiv:1506.03365v2 [cs.cv] 19 Jun 2015 Princeton
More informationAn 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 informationIFT3395/6390. 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 informationSense 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 informationGPU-Based Deep Learning Inference:
Whitepaper GPU-Based Deep Learning Inference: A Performance and Power Analysis November 2015 1 Contents Abstract... 3 Introduction... 3 Inference versus Training... 4 GPUs Excel at Neural Network Inference...
More informationProgramming 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 informationUsing Convolutional Neural Networks for Image Recognition
Using Convolutional Neural Networks for Image Recognition By Samer Hijazi, Rishi Kumar, and Chris Rowen, IP Group, Cadence Convolutional neural networks (CNNs) are widely used in pattern- and image-recognition
More informationMulti-Column Deep Neural Network for Traffic Sign Classification
Multi-Column Deep Neural Network for Traffic Sign Classification Dan Cireşan, Ueli Meier, Jonathan Masci and Jürgen Schmidhuber IDSIA - USI - SUPSI Galleria 2, Manno - Lugano 6928, Switzerland Abstract
More informationarxiv:1412.1897v4 [cs.cv] 2 Apr 2015
Full Citation: Nguyen A, Yosinski J, Clune J. Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images. In Computer Vision and Pattern Recognition (CVPR 15), IEEE,
More informationObject Detection in Video using Faster R-CNN
Object Detection in Video using Faster R-CNN Prajit Ramachandran University of Illinois at Urbana-Champaign prmchnd2@illinois.edu Abstract Convolutional neural networks (CNN) currently dominate the computer
More informationFeed-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 informationNeural 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 informationProbabilistic 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 informationTattoo Detection for Soft Biometric De-Identification Based on Convolutional NeuralNetworks
1 Tattoo Detection for Soft Biometric De-Identification Based on Convolutional NeuralNetworks Tomislav Hrkać, Karla Brkić, Zoran Kalafatić Faculty of Electrical Engineering and Computing University of
More informationBig 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 informationMachine 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 informationThe Applications of Deep Learning on Traffic Identification
The Applications of Deep Learning on Traffic Identification Zhanyi Wang wangzhanyi@360.cn Abstract Generally speaking, most systems of network traffic identification are based on features. The features
More informationChapter 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 informationSSD: Single Shot MultiBox Detector
SSD: Single Shot MultiBox Detector Wei Liu 1, Dragomir Anguelov 2, Dumitru Erhan 3, Christian Szegedy 3, Scott Reed 4, Cheng-Yang Fu 1, Alexander C. Berg 1 1 UNC Chapel Hill 2 Zoox Inc. 3 Google Inc. 4
More informationarxiv:1409.1556v6 [cs.cv] 10 Apr 2015
VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION Karen Simonyan & Andrew Zisserman + Visual Geometry Group, Department of Engineering Science, University of Oxford {karen,az}@robots.ox.ac.uk
More informationDeepPlaylist: Using Recurrent Neural Networks to Predict Song Similarity
DeepPlaylist: Using Recurrent Neural Networks to Predict Song Similarity Anusha Balakrishnan Stanford University anusha@cs.stanford.edu Kalpit Dixit Stanford University kalpit@stanford.edu Abstract The
More informationClass #6: Non-linear classification. ML4Bio 2012 February 17 th, 2012 Quaid Morris
Class #6: Non-linear classification ML4Bio 2012 February 17 th, 2012 Quaid Morris 1 Module #: Title of Module 2 Review Overview Linear separability Non-linear classification Linear Support Vector Machines
More informationApplying Deep Learning to Car Data Logging (CDL) and Driver Assessor (DA) October 22-Oct-15
Applying Deep Learning to Car Data Logging (CDL) and Driver Assessor (DA) October 22-Oct-15 GENIVI is a registered trademark of the GENIVI Alliance in the USA and other countries Copyright GENIVI Alliance
More informationLecture 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 informationImage Super-Resolution Using Deep Convolutional Networks
1 Image Super-Resolution Using Deep Convolutional Networks Chao Dong, Chen Change Loy, Member, IEEE, Kaiming He, Member, IEEE, and Xiaoou Tang, Fellow, IEEE arxiv:1501.00092v3 [cs.cv] 31 Jul 2015 Abstract
More informationTransfer Learning for Latin and Chinese Characters with Deep Neural Networks
Transfer Learning for Latin and Chinese Characters with Deep Neural Networks Dan C. Cireşan IDSIA USI-SUPSI Manno, Switzerland, 6928 Email: dan@idsia.ch Ueli Meier IDSIA USI-SUPSI Manno, Switzerland, 6928
More informationPredict 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 informationAnalecta 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 informationMACHINE LEARNING IN HIGH ENERGY PHYSICS
MACHINE LEARNING IN HIGH ENERGY PHYSICS LECTURE #1 Alex Rogozhnikov, 2015 INTRO NOTES 4 days two lectures, two practice seminars every day this is introductory track to machine learning kaggle competition!
More informationCSCI567 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 informationLatest Advances in Deep Learning. Yao Chou
Latest Advances in Deep Learning Yao Chou Outline Introduction Images Classification Object Detection R-CNN Traditional Feature Descriptor Selective Search Implementation Latest Application Deep Learning
More informationSTA 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 informationTask-driven Progressive Part Localization for Fine-grained Recognition
Task-driven Progressive Part Localization for Fine-grained Recognition Chen Huang Zhihai He chenhuang@mail.missouri.edu University of Missouri hezhi@missouri.edu Abstract In this paper we propose a task-driven
More informationNeural 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 informationLARGE-SCALE MALWARE CLASSIFICATION USING RANDOM PROJECTIONS AND NEURAL NETWORKS
LARGE-SCALE MALWARE CLASSIFICATION USING RANDOM PROJECTIONS AND NEURAL NETWORKS George E. Dahl University of Toronto Department of Computer Science Toronto, ON, Canada Jack W. Stokes, Li Deng, Dong Yu
More informationA 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 informationLecture 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 informationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
1 Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun arxiv:1506.01497v3 [cs.cv] 6 Jan 2016 Abstract State-of-the-art object
More informationUSTC Course for students entering Clemson F2013 Equivalent Clemson Course Counts for Clemson MS Core Area. CPSC 822 Case Study in Operating Systems
USTC Course for students entering Clemson F2013 Equivalent Clemson Course Counts for Clemson MS Core Area 398 / SE05117 Advanced Cover software lifecycle: waterfall model, V model, spiral model, RUP and
More informationFast Accurate Fish Detection and Recognition of Underwater Images with Fast R-CNN
Fast Accurate Fish Detection and Recognition of Underwater Images with Fast R-CNN Xiu Li 1, 2, Min Shang 1, 2, Hongwei Qin 1, 2, Liansheng Chen 1, 2 1. Department of Automation, Tsinghua University, Beijing
More informationLinear 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 informationRecurrent 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 informationMethods and Applications for Distance Based ANN Training
Methods and Applications for Distance Based ANN Training Christoph Lassner, Rainer Lienhart Multimedia Computing and Computer Vision Lab Augsburg University, Universitätsstr. 6a, 86159 Augsburg, Germany
More informationIntroduction 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 informationImpact of Feature Selection on the Performance of Wireless Intrusion Detection Systems
2009 International Conference on Computer Engineering and Applications IPCSIT vol.2 (2011) (2011) IACSIT Press, Singapore Impact of Feature Selection on the Performance of ireless Intrusion Detection Systems
More informationImage Caption Generator Based On Deep Neural Networks
Image Caption Generator Based On Deep Neural Networks Jianhui Chen CPSC 503 CS Department Wenqiang Dong CPSC 503 CS Department Minchen Li CPSC 540 CS Department Abstract In this project, we systematically
More informationDeep learning applications and challenges in big data analytics
Najafabadi et al. Journal of Big Data (2015) 2:1 DOI 10.1186/s40537-014-0007-7 RESEARCH Open Access Deep learning applications and challenges in big data analytics Maryam M Najafabadi 1, Flavio Villanustre
More informationPATTERN 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 informationParallel Data Mining. Team 2 Flash Coders Team Research Investigation Presentation 2. Foundations of Parallel Computing Oct 2014
Parallel Data Mining Team 2 Flash Coders Team Research Investigation Presentation 2 Foundations of Parallel Computing Oct 2014 Agenda Overview of topic Analysis of research papers Software design Overview
More informationAn Introduction to Deep Learning
Thought Leadership Paper Predictive Analytics An Introduction to Deep Learning Examining the Advantages of Hierarchical Learning Table of Contents 4 The Emergence of Deep Learning 7 Applying Deep-Learning
More informationSimple 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 informationarxiv:1604.08893v1 [cs.cv] 29 Apr 2016
Faster R-CNN Features for Instance Search Amaia Salvador, Xavier Giró-i-Nieto, Ferran Marqués Universitat Politècnica de Catalunya (UPC) Barcelona, Spain {amaia.salvador,xavier.giro}@upc.edu Shin ichi
More informationSupport Vector Pruning with SortedVotes for Large-Scale Datasets
Support Vector Pruning with SortedVotes for Large-Scale Datasets Frerk Saxen, Konrad Doll and Ulrich Brunsmann University of Applied Sciences Aschaffenburg, Germany Email: {Frerk.Saxen, Konrad.Doll, Ulrich.Brunsmann}@h-ab.de
More information