Tasks ADAS. Self Driving. Non-machine Learning. Traditional MLP. Machine-Learning based method. Supervised CNN. Methods. Deep-Learning based
|
|
|
- Kristian Hutchinson
- 5 years ago
- Views:
Transcription
1 UNDERSTANDING CNN
2 ADAS Tasks Self Driving Localizati on Perception Planning/ Control Driver state Vehicle Diagnosis Smart factory Methods Traditional Deep-Learning based Non-machine Learning Machine-Learning based method Supervised MLP CNN RNN (LSTM) DNN Reinforcement GPS, SLAM Pedestrian detection (HOG+SVM) Detection/ Segmentat ion/classif ication Dry/wet road classificati on Optimal control End-toend Learning End-toend Learning Unsupervised
3 TENSORFLOW-POWERED CUCUMBER SORTER
4 Cucumber sorting Each cucumber has different color, shape, quality and freshness. At Makoto's farm, they sort them into nine different classes, and his mother sorts them all herself spending up to eight hours per day at peak harvesting times.
5 Cucumber sorting You have to look at not only the size and thickness, but also the color, texture, small scratches, whether or not they are crooked and whether they have prickles. It takes months to learn the system and you can't just hire part-time workers during the busiest period. I myself only recently learned to sort cucumbers well, Makoto said. Makoto doesn t think sorting is an essential task for cucumber farmers. "Farmers want to focus and spend their time on growing delicious vegetables. I'd like to automate the sorting tasks before taking the farm business over from my parents.
6 Tensorflow-powered cucumber sorter Makoto used the sample TensorFlow code Deep MNIST for Experts with minor modifications to the convolution, pooling and last layers, changing the network design to adapt to the pixel format of cucumber images and the number of cucumber classes.
7 Cucumber sorter by Makoto Koike
8 MNIST & LENET
9 MNIST dataset handwritten digits a training set of 60,000 examples 28x28 images
10 LeNet Yann LeCun and his collaborators developed a recognizer for handwritten digits by using back-propagation in a feed-forward net
11 CNN BUILDING BLOCKS
12 Convolution
13 Convolutions in CNNs
14 Pooling Max vs Average pooling
15 DEEP MNIST FOR EXPERTS
16 Deep MNIST for Experts
17 Deep MNIST for Experts
18 LeNet #(Parameter) = 3,274,634 Layer C1 C2 1 2 Weight ,200 3,211,264 10,240 Bias ,024 10
19 The 82 errors by LeNet5
20
21 Feature map results
22 Learned Filters Trained 32 filters on C1 layer
23 Learned Filters Filtered result ReLU Filtered result ReLU Filtered result ReLU Filtered result ReLU Filtered result ReLU Filtered result ReLU Filtered result ReLU Filtered result ReLU
24 TensorFlow codes LeNet tensorflow codes
25 IMAGE CLASSIFICATION
26 Image Classification (ImageNet)
27 ALEXNET
28 AlexNet AlexNet: won the 2012 ImageNet competition by making 40% less error than the next best competitor It is composed of 5 convolutional layers The input is a color RGB image Computation is divided over 2 GPU architectures
29 AlexNet results AlexNet TensorFlow codes and some results
30 AlexNet Visualization Filters learned by the first convolutional layer. The top half corresponds to the layer on one GPU, the bottom on the other. From Krizehvsky et al. (2012) Each of the 96 filters is of size [11x11x3]
31 VISUALIZATION
32 Motivation It is well known that Artificial Neural Networks show remarkable performance in image classification However, we actually understand little of why certain models work and others don t There have been some attempts to visualize at each layer in the neural network - to know how neural networks work and what each layer has learned
33 Why is this important? There is a need of training networks with information we want to learn But this program couldn t ignore what we don t care about
34 Visualization method Deconvolution Matthew D. Zeiler and Rob Fergus, Visualizing and Understanding Convolutional Networks, ECCV 2014 Input optimization Naïve visualization Low/High frequency normalization With image prior With Laplacian (pyramid gradient) normalization
35 Channel 1 Channel 2 Channel 3 Channel n-1 Channel n Channel n+1 Naïve visualization GoogLeNet T: Selected layer and channel Objective function: L = mean(t) GRADIENT ASCENT: img new img old + α L img img old
36 Channel 1 Channel 2 Channel 3 Channel n-1 Channel n Channel n+1 Naïve visualization GoogLeNet Initial input: an arbitrary noise image Selected (layer, channel) L=34.99 i =0 L= i =9 L= i =19 GRADIENT ASCENT Output images
37 Channel 1 Channel 2 Channel 3 Channel n-1 Channel n Channel n+1 Single neuron activation GoogLeNet img Initial input: an arbitrary noise image T: Selected (layer,channel, position) i =0 i =4 i =9 i =14 i =19 i =24 i =29 i =34 i =39 i =44 i =49
38 Single neuron activation results iteration 3a_3x3_pre_relu 4d_3x3_bottleneck_pre_relu 5a_pool_reduce_pre_relu layer
39 Examples of naïve feature visualization input localresponsenorm localresponsenorm GoogLeNet
40 Examples of naïve feature visualization input localresponsenorm localresponsenorm GoogLeNet
41 Examples of naïve feature visualization input localresponsenorm localresponsenorm GoogLeNet
42 Examples of naïve feature visualization input localresponsenorm localresponsenorm GoogLeNet
43 Examples of naïve feature visualization input localresponsenorm localresponsenorm GoogLeNet
44 Examples of naïve feature visualization input localresponsenorm localresponsenorm GoogLeNet
45 Examples of naïve feature visualization input localresponsenorm localresponsenorm GoogLeNet
46 Examples of naïve feature visualization input localresponsenorm localresponsenorm GoogLeNet
47 Examples of naïve feature visualization. input localresponsenorm localresponsenorm GoogLeNet
48 LOW/HIGH FREQUENCY NORMALIZATION
49 Gradient normalization GRADIENT Computation Initial input: an arbitrary noise image Low frequency normalization merge Normalized gradient High frequency normalization
50 Laplacian pyramid
51 Convergence example L=102.42
52 Result of Laplacian pyramid method input localresponsenorm localresponsenorm GoogLeNet
53 Result of Laplacian pyramid method input localresponsenorm localresponsenorm GoogLeNet
54 Result of Laplacian pyramid method input localresponsenorm localresponsenorm GoogLeNet
55 Result of Laplacian pyramid method input localresponsenorm localresponsenorm GoogLeNet
56 Result of Laplacian pyramid method input localresponsenorm localresponsenorm GoogLeNet
57 Result of Laplacian pyramid method input localresponsenorm localresponsenorm GoogLeNet
58 Result of Laplacian pyramid method input localresponsenorm localresponsenorm GoogLeNet
59 Result of Laplacian pyramid method input localresponsenorm localresponsenorm GoogLeNet
60 Result of Laplacian pyramid method input localresponsenorm localresponsenorm GoogLeNet
61 Result of Laplacian pyramid method. input localresponsenorm localresponsenorm GoogLeNet
62 Results with two channels
63 Summary x x CNN layer y CNN layer y layer Feature type Feature type Complex features
64 DEEPDREAM
65 DeepDream Square cost function vs vs 100 2
66 Examples (all feature maps in a layer)
67 DeepDream example
68 DeepDream example
69
70 TOPICS IN CNN
71 COMPARISON
72 AlexNet VS VGG-19 VS GoogLeNet Parameters Operations (MACs) *Top-1 accuracy (%) *Top-5 accuracy % AlexNet 60 M 832 M VGG M 19,632 M GoogLeNet 6.8 M 1,502 M *Evaluated with ImageNet2012 *
73 Comparison
74 VISUALIZING IMAGE CLASSIFICATION MODEL
75 Inputs maximizing class score S c I λ I 2 Objective Function (to be maximized) K. Simonyan, A. Vedaldi, A. Zisserman, Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps, ICLR Workshop 2014
76 Inputs maximizing class score S c I λ I 2 Objective Function (to be maximized) Goose class
77 Maximizing class score S c I λ I 2 Objective Function (to be maximized) Goose class
78 Inputs maximizing class score dumbbell cup dalmatian bell pepper lemon husky
79 Inputs maximizing class score computer keyboard kit fox limousine Washing machine goose ostrich
80 SALIENCY
81 Saliency visualization Linear score model for class c: w : importance of corresponding pixels of I for class c
82 Saliency visualization Dog Class Objective Function
83 Saliency visualization Dog Class Differentiation Objective Function S c (I 0 ) I 0 =
84 Saliency visualization I 0 = saliency map
85 yacht dog monkey washing machine cow building
86 A NEURAL ALGORITHM OF ARTISTIC STYLE
87 Style Loss? Content Loss Gatys, Leon A., Alexander S. Ecker, and Matthias Bethge. "A neural algorithm of artistic style." arxiv preprint arxiv: (2015).
88 Style Loss? Content Loss Gatys, Leon A., Alexander S. Ecker, and Matthias Bethge. "A neural algorithm of artistic style." arxiv preprint arxiv: (2015).
89 Style Loss? Content Loss Gatys, Leon A., Alexander S. Ecker, and Matthias Bethge. "A neural algorithm of artistic style." arxiv preprint arxiv: (2015).
90 Artistic style
91 Artistic style
92 예제코드 Tensorflow codes Tensorflow codes
93 ADVERSARIAL EXAMPLE
94 예제코드 Codes
Neural Network Back-propagation HYUNG IL KOO
Neural Network Back-propagation HYUNG IL KOO Hidden Layer Representations Backpropagation has an ability to discover useful intermediate representations at the hidden unit layers inside the networks which
UNSUPERVISED LEARNING
UNSUPERVISED LEARNING Topics Layer-wise (unsupervised) pre-training Restricted Boltzmann Machines Auto-encoders LAYER-WISE (UNSUPERVISED) PRE-TRAINING Breakthrough in 2006 Layer-wise (unsupervised) pre-training
Understanding CNNs using visualisation and transformation analysis
Understanding CNNs using visualisation and transformation analysis Andrea Vedaldi Medical Imaging Summer School August 2016 Image representations 2 encoder Φ representation An encoder maps the data into
Understanding How ConvNets See
Understanding How ConvNets See Slides from Andrej Karpathy Springerberg et al, Striving for Simplicity: The All Convolutional Net (ICLR 2015 workshops) CSC321: Intro to Machine Learning and Neural Networks,
Introduction to Convolutional Neural Networks (CNNs)
Introduction to Convolutional Neural Networks (CNNs) nojunk@snu.ac.kr http://mipal.snu.ac.kr Department of Transdisciplinary Studies Seoul National University, Korea Jan. 2016 Many slides are from Fei-Fei
Explaining Machine Learning Decisions
Explaining Machine Learning Decisions Grégoire Montavon, TU Berlin Joint work with: Wojciech Samek, Klaus-Robert Müller, Sebastian Lapuschkin, Alexander Binder 18/09/2018 Intl. Workshop ML & AI, Telecom
Fine-grained Classification
Fine-grained Classification Marcel Simon Department of Mathematics and Computer Science, Germany marcel.simon@uni-jena.de http://www.inf-cv.uni-jena.de/ Seminar Talk 23.06.2015 Outline 1 Motivation 2 3
Convolutional Neural Network Architecture
Convolutional Neural Network Architecture Zhisheng Zhong Feburary 2nd, 2018 Zhisheng Zhong Convolutional Neural Network Architecture Feburary 2nd, 2018 1 / 55 Outline 1 Introduction of Convolution Motivation
Lecture 7 Convolutional Neural Networks
Lecture 7 Convolutional Neural Networks CMSC 35246: Deep Learning Shubhendu Trivedi & Risi Kondor University of Chicago April 17, 2017 We saw before: ŷ x 1 x 2 x 3 x 4 A series of matrix multiplications:
Grundlagen der Künstlichen Intelligenz
Grundlagen der Künstlichen Intelligenz Neural networks Daniel Hennes 21.01.2018 (WS 2017/18) University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Logistic regression Neural networks Perceptron
Deep Learning (CNNs)
10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Deep Learning (CNNs) Deep Learning Readings: Murphy 28 Bishop - - HTF - - Mitchell
Artificial Neural Networks D B M G. Data Base and Data Mining Group of Politecnico di Torino. Elena Baralis. Politecnico di Torino
Artificial Neural Networks Data Base and Data Mining Group of Politecnico di Torino Elena Baralis Politecnico di Torino Artificial Neural Networks Inspired to the structure of the human brain Neurons as
Machine Learning for Computer Vision 8. Neural Networks and Deep Learning. Vladimir Golkov Technical University of Munich Computer Vision Group
Machine Learning for Computer Vision 8. Neural Networks and Deep Learning Vladimir Golkov Technical University of Munich Computer Vision Group INTRODUCTION Nonlinear Coordinate Transformation http://cs.stanford.edu/people/karpathy/convnetjs/
Convolutional Neural Network. Hung-yi Lee
al Neural Network Hung-yi Lee Why CNN for Image? [Zeiler, M. D., ECCV 2014] x 1 x 2 Represented as pixels x N The most basic classifiers Use 1 st layer as module to build classifiers Use 2 nd layer as
Artificial Neural Networks. Introduction to Computational Neuroscience Tambet Matiisen
Artificial Neural Networks Introduction to Computational Neuroscience Tambet Matiisen 2.04.2018 Artificial neural network NB! Inspired by biology, not based on biology! Applications Automatic speech recognition
Lecture 17: Neural Networks and Deep Learning
UVA CS 6316 / CS 4501-004 Machine Learning Fall 2016 Lecture 17: Neural Networks and Deep Learning Jack Lanchantin Dr. Yanjun Qi 1 Neurons 1-Layer Neural Network Multi-layer Neural Network Loss Functions
Tutorial on Methods for Interpreting and Understanding Deep Neural Networks. Part 3: Applications & Discussion
Tutorial on Methods for Interpreting and Understanding Deep Neural Networks W. Samek, G. Montavon, K.-R. Müller Part 3: Applications & Discussion ICASSP 2017 Tutorial W. Samek, G. Montavon & K.-R. Müller
Neural Networks 2. 2 Receptive fields and dealing with image inputs
CS 446 Machine Learning Fall 2016 Oct 04, 2016 Neural Networks 2 Professor: Dan Roth Scribe: C. Cheng, C. Cervantes Overview Convolutional Neural Networks Recurrent Neural Networks 1 Introduction There
Classification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses about the label (Top-5 error) No Bounding Box
ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton Motivation Classification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses
Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net
Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net Supplementary Material Xingang Pan 1, Ping Luo 1, Jianping Shi 2, and Xiaoou Tang 1 1 CUHK-SenseTime Joint Lab, The Chinese University
Convolutional Neural Networks
Convolutional Neural Networks Books» http://www.deeplearningbook.org/ Books http://neuralnetworksanddeeplearning.com/.org/ reviews» http://www.deeplearningbook.org/contents/linear_algebra.html» http://www.deeplearningbook.org/contents/prob.html»
CS 179: LECTURE 16 MODEL COMPLEXITY, REGULARIZATION, AND CONVOLUTIONAL NETS
CS 179: LECTURE 16 MODEL COMPLEXITY, REGULARIZATION, AND CONVOLUTIONAL NETS LAST TIME Intro to cudnn Deep neural nets using cublas and cudnn TODAY Building a better model for image classification Overfitting
Spatial Transformer Networks
BIL722 - Deep Learning for Computer Vision Spatial Transformer Networks Max Jaderberg Andrew Zisserman Karen Simonyan Koray Kavukcuoglu Contents Introduction to Spatial Transformers Related Works Spatial
<Special Topics in VLSI> Learning for Deep Neural Networks (Back-propagation)
Learning for Deep Neural Networks (Back-propagation) Outline Summary of Previous Standford Lecture Universal Approximation Theorem Inference vs Training Gradient Descent Back-Propagation
Some Applications of Machine Learning to Astronomy. Eduardo Bezerra 20/fev/2018
Some Applications of Machine Learning to Astronomy Eduardo Bezerra ebezerra@cefet-rj.br 20/fev/2018 Overview 2 Introduction Definition Neural Nets Applications do Astronomy Ads: Machine Learning Course
Machine Learning. Boris
Machine Learning Boris Nadion boris@astrails.com @borisnadion @borisnadion boris@astrails.com astrails http://astrails.com awesome web and mobile apps since 2005 terms AI (artificial intelligence)
Introduction to Machine Learning (67577)
Introduction to Machine Learning (67577) Shai Shalev-Shwartz School of CS and Engineering, The Hebrew University of Jerusalem Deep Learning Shai Shalev-Shwartz (Hebrew U) IML Deep Learning Neural Networks
Convolutional Neural Networks II. Slides from Dr. Vlad Morariu
Convolutional Neural Networks II Slides from Dr. Vlad Morariu 1 Optimization Example of optimization progress while training a neural network. (Loss over mini-batches goes down over time.) 2 Learning rate
SGD and Deep Learning
SGD and Deep Learning Subgradients Lets make the gradient cheating more formal. Recall that the gradient is the slope of the tangent. f(w 1 )+rf(w 1 ) (w w 1 ) Non differentiable case? w 1 Subgradients
Bayesian Networks (Part I)
10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Bayesian Networks (Part I) Graphical Model Readings: Murphy 10 10.2.1 Bishop 8.1,
Machine Learning for Signal Processing Neural Networks Continue. Instructor: Bhiksha Raj Slides by Najim Dehak 1 Dec 2016
Machine Learning for Signal Processing Neural Networks Continue Instructor: Bhiksha Raj Slides by Najim Dehak 1 Dec 2016 1 So what are neural networks?? Voice signal N.Net Transcription Image N.Net Text
arxiv: v1 [cs.cv] 11 May 2015 Abstract
![arxiv: v1 [cs.cv] 11 May 2015 Abstract](/thumbs/80/80674557.jpg "arxiv: v1 [cs.cv] 11 May 2015 Abstract")
Training Deeper Convolutional Networks with Deep Supervision Liwei Wang Computer Science Dept UIUC lwang97@illinois.edu Chen-Yu Lee ECE Dept UCSD chl260@ucsd.edu Zhuowen Tu CogSci Dept UCSD ztu0@ucsd.edu
Supervised Deep Learning
Supervised Deep Learning Joana Frontera-Pons Grigorios Tsagkatakis Dictionary Learning on Manifolds workshop Nice, September 2017 Supervised Learning Data Labels Model Prediction Spiral Exploiting prior
Convolutional neural networks
11-1: Convolutional neural networks Prof. J.C. Kao, UCLA Convolutional neural networks Motivation Biological inspiration Convolution operation Convolutional layer Padding and stride CNN architecture 11-2:
Jakub Hajic Artificial Intelligence Seminar I
Jakub Hajic Artificial Intelligence Seminar I. 11. 11. 2014 Outline Key concepts Deep Belief Networks Convolutional Neural Networks A couple of questions Convolution Perceptron Feedforward Neural Network
Neural Networks. Single-layer neural network. CSE 446: Machine Learning Emily Fox University of Washington March 10, /9/17
3/9/7 Neural Networks Emily Fox University of Washington March 0, 207 Slides adapted from Ali Farhadi (via Carlos Guestrin and Luke Zettlemoyer) Single-layer neural network 3/9/7 Perceptron as a neural
Deep Learning Basics Lecture 7: Factor Analysis. Princeton University COS 495 Instructor: Yingyu Liang
Deep Learning Basics Lecture 7: Factor Analysis Princeton University COS 495 Instructor: Yingyu Liang Supervised v.s. Unsupervised Math formulation for supervised learning Given training data x i, y i
Memory-Augmented Attention Model for Scene Text Recognition
Memory-Augmented Attention Model for Scene Text Recognition Cong Wang 1,2, Fei Yin 1,2, Cheng-Lin Liu 1,2,3 1 National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences
Theories of Deep Learning
Theories of Deep Learning Lecture 02 Donoho, Monajemi, Papyan Department of Statistics Stanford Oct. 4, 2017 1 / 50 Stats 385 Fall 2017 2 / 50 Stats 285 Fall 2017 3 / 50 Course info Wed 3:00-4:20 PM in
CSE446: Neural Networks Spring Many slides are adapted from Carlos Guestrin and Luke Zettlemoyer
CSE446: Neural Networks Spring 2017 Many slides are adapted from Carlos Guestrin and Luke Zettlemoyer Human Neurons Switching time ~ 0.001 second Number of neurons 10 10 Connections per neuron 10 4-5 Scene
CSC321 Lecture 16: ResNets and Attention
CSC321 Lecture 16: ResNets and Attention Roger Grosse Roger Grosse CSC321 Lecture 16: ResNets and Attention 1 / 24 Overview Two topics for today: Topic 1: Deep Residual Networks (ResNets) This is the state-of-the
Deep Learning for Automatic Speech Recognition Part II
Deep Learning for Automatic Speech Recognition Part II Xiaodong Cui IBM T. J. Watson Research Center Yorktown Heights, NY 10598 Fall, 2018 Outline A brief revisit of sampling, pitch/formant and MFCC DNN-HMM
Introduction to Convolutional Neural Networks 2018 / 02 / 23
Introduction to Convolutional Neural Networks 2018 / 02 / 23 Buzzword: CNN Convolutional neural networks (CNN, ConvNet) is a class of deep, feed-forward (not recurrent) artificial neural networks that
CS 229 Project Final Report: Reinforcement Learning for Neural Network Architecture Category : Theory & Reinforcement Learning
CS 229 Project Final Report: Reinforcement Learning for Neural Network Architecture Category : Theory & Reinforcement Learning Lei Lei Ruoxuan Xiong December 16, 2017 1 Introduction Deep Neural Network
Sajid Anwar, Kyuyeon Hwang and Wonyong Sung
Sajid Anwar, Kyuyeon Hwang and Wonyong Sung Department of Electrical and Computer Engineering Seoul National University Seoul, 08826 Korea Email: sajid@dsp.snu.ac.kr, khwang@dsp.snu.ac.kr, wysung@snu.ac.kr
Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers
Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers Alexander Binder 1, Grégoire Montavon 2, Sebastian Lapuschkin 3, Klaus-Robert Müller 2,4, and Wojciech Samek 3 1 ISTD
CS 1674: Intro to Computer Vision. Final Review. Prof. Adriana Kovashka University of Pittsburgh December 7, 2016
CS 1674: Intro to Computer Vision Final Review Prof. Adriana Kovashka University of Pittsburgh December 7, 2016 Final info Format: multiple-choice, true/false, fill in the blank, short answers, apply an
What Do Neural Networks Do? MLP Lecture 3 Multi-layer networks 1
What Do Neural Networks Do? MLP Lecture 3 Multi-layer networks 1 Multi-layer networks Steve Renals Machine Learning Practical MLP Lecture 3 7 October 2015 MLP Lecture 3 Multi-layer networks 2 What Do Single
Maxout Networks. Hien Quoc Dang
Maxout Networks Hien Quoc Dang Outline Introduction Maxout Networks Description A Universal Approximator & Proof Experiments with Maxout Why does Maxout work? Conclusion 10/12/13 Hien Quoc Dang Machine
RAGAV VENKATESAN VIJETHA GATUPALLI BAOXIN LI NEURAL DATASET GENERALITY
RAGAV VENKATESAN VIJETHA GATUPALLI BAOXIN LI NEURAL DATASET GENERALITY SIFT HOG ALL ABOUT THE FEATURES DAISY GABOR AlexNet GoogleNet CONVOLUTIONAL NEURAL NETWORKS VGG-19 ResNet FEATURES COMES FROM DATA
Demystifying deep learning. Artificial Intelligence Group Department of Computer Science and Technology, University of Cambridge, UK
Demystifying deep learning Petar Veličković Artificial Intelligence Group Department of Computer Science and Technology, University of Cambridge, UK London Data Science Summit 20 October 2017 Introduction
Very Deep Residual Networks with Maxout for Plant Identification in the Wild Milan Šulc, Dmytro Mishkin, Jiří Matas
Very Deep Residual Networks with Maxout for Plant Identification in the Wild Milan Šulc, Dmytro Mishkin, Jiří Matas Center for Machine Perception Department of Cybernetics Faculty of Electrical Engineering
arxiv: v1 [cs.cv] 14 Sep 2016
![arxiv: v1 [cs.cv] 14 Sep 2016](/thumbs/89/100152104.jpg "arxiv: v1 [cs.cv] 14 Sep 2016")
Understanding Convolutional Neural Networks with A Mathematical Model arxiv:1609.04112v1 [cs.cv] 14 Sep 2016 Abstract C.-C. Jay Kuo Ming-Hsieh Department of Electrical Engineering University of Southern
Differentiable Fine-grained Quantization for Deep Neural Network Compression
Differentiable Fine-grained Quantization for Deep Neural Network Compression Hsin-Pai Cheng hc218@duke.edu Yuanjun Huang University of Science and Technology of China Anhui, China yjhuang@mail.ustc.edu.cn
GENERATIVE MODELING OF CONVOLUTIONAL NEU-
GENERATIVE MODELING OF CONVOLUTIONAL NEU- RAL NETWORKS Jifeng Dai Microsoft Research jifdai@microsoft.com Yang Lu and Ying Nian Wu University of California, Los Angeles {yanglv, ywu}@stat.ucla.edu ABSTRACT
Index. Santanu Pattanayak 2017 S. Pattanayak, Pro Deep Learning with TensorFlow,
Index A Activation functions, neuron/perceptron binary threshold activation function, 102 103 linear activation function, 102 rectified linear unit, 106 sigmoid activation function, 103 104 SoftMax activation
Reading Group on Deep Learning Session 2
Reading Group on Deep Learning Session 2 Stephane Lathuiliere & Pablo Mesejo 10 June 2016 1/39 Chapter Structure Introduction. 5.1. Feed-forward Network Functions. 5.2. Network Training. 5.3. Error Backpropagation.
Advancing Machine Learning and AI with Geography and GIS. Robert Kircher
Advancing Machine Learning and AI with Geography and GIS Robert Kircher rkircher@esri.com Welcome & Thanks GIS is expected to do more, faster. see where find where predict where locate, connect WHERE route
Asaf Bar Zvi Adi Hayat. Semantic Segmentation
Asaf Bar Zvi Adi Hayat Semantic Segmentation Today s Topics Fully Convolutional Networks (FCN) (CVPR 2015) Conditional Random Fields as Recurrent Neural Networks (ICCV 2015) Gaussian Conditional random
Lecture 8: Introduction to Deep Learning: Part 2 (More on backpropagation, and ConvNets)
COS 402 Machine Learning and Artificial Intelligence Fall 2016 Lecture 8: Introduction to Deep Learning: Part 2 (More on backpropagation, and ConvNets) Sanjeev Arora Elad Hazan Recap: Structure of a deep
arxiv: v1 [cs.lg] 7 Dec 2017
![arxiv: v1 [cs.lg] 7 Dec 2017](/thumbs/94/119674130.jpg "arxiv: v1 [cs.lg] 7 Dec 2017")
Take it in your stride: Do we need striding in CNNs? Chen Kong imon Lucey Carnegie Mellon University {chenk, slucey}@andrew.cmu.edu arxiv:1712.02502v1 [cs.lg] 7 Dec 2017 Abstract ince their inception,
Mitosis Detection in Breast Cancer Histology Images with Multi Column Deep Neural Networks
Mitosis Detection in Breast Cancer Histology Images with Multi Column Deep Neural Networks IDSIA, Lugano, Switzerland dan.ciresan@gmail.com Dan C. Cireşan and Alessandro Giusti DNN for Visual Pattern Recognition
Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
1 Explaining NonLinear Classification Decisions with Deep Taylor Decomposition Grégoire Montavon, Sebastian Bach, Alexander Binder, Wojciech Samek, and Klaus-Robert Müller arxiv:1512.2479v1 [cs.lg] 8 Dec
Lecture 35: Optimization and Neural Nets
Lecture 35: Optimization and Neural Nets CS 4670/5670 Sean Bell DeepDream [Google, Inceptionism: Going Deeper into Neural Networks, blog 2015] Aside: CNN vs ConvNet Note: There are many papers that use
Artificial Neural Networks
Artificial Neural Networks Oliver Schulte - CMPT 310 Neural Networks Neural networks arise from attempts to model human/animal brains Many models, many claims of biological plausibility We will focus on
A practical theory for designing very deep convolutional neural networks. Xudong Cao.
A practical theory for designing very deep convolutional neural networks Xudong Cao notcxd@gmail.com Abstract Going deep is essential for deep learning. However it is not easy, there are many ways of going
Deep Learning Lecture 2
Fall 2016 Machine Learning CMPSCI 689 Deep Learning Lecture 2 Sridhar Mahadevan Autonomous Learning Lab UMass Amherst COLLEGE Outline of lecture New type of units Convolutional units, Rectified linear
Neural Architectures for Image, Language, and Speech Processing
Neural Architectures for Image, Language, and Speech Processing Karl Stratos June 26, 2018 1 / 31 Overview Feedforward Networks Need for Specialized Architectures Convolutional Neural Networks (CNNs) Recurrent
PRUNING CONVOLUTIONAL NEURAL NETWORKS. Pavlo Molchanov Stephen Tyree Tero Karras Timo Aila Jan Kautz
PRUNING CONVOLUTIONAL NEURAL NETWORKS Pavlo Molchanov Stephen Tyree Tero Karras Timo Aila Jan Kautz 2017 WHY WE CAN PRUNE CNNS? 2 WHY WE CAN PRUNE CNNS? Optimization failures : Some neurons are "dead":
Machine Learning for Large-Scale Data Analysis and Decision Making A. Neural Networks Week #6
Machine Learning for Large-Scale Data Analysis and Decision Making 80-629-17A Neural Networks Week #6 Today Neural Networks A. Modeling B. Fitting C. Deep neural networks Today s material is (adapted)
An overview of deep learning methods for genomics
An overview of deep learning methods for genomics Matthew Ploenzke STAT115/215/BIO/BIST282 Harvard University April 19, 218 1 Snapshot 1. Brief introduction to convolutional neural networks What is deep
Top Tagging with Lorentz Boost Networks and Simulation of Electromagnetic Showers with a Wasserstein GAN
Top Tagging with Lorentz Boost Networks and Simulation of Electromagnetic Showers with a Wasserstein GAN Y. Rath, M. Erdmann, B. Fischer, L. Geiger, E. Geiser, J.Glombitza, D. Noll, T. Quast, M. Rieger,
Deep Learning: a gentle introduction
Deep Learning: a gentle introduction Jamal Atif jamal.atif@dauphine.fr PSL, Université Paris-Dauphine, LAMSADE February 8, 206 Jamal Atif (Université Paris-Dauphine) Deep Learning February 8, 206 / Why
Machine Learning. Neural Networks. (slides from Domingos, Pardo, others)
Machine Learning Neural Networks (slides from Domingos, Pardo, others) For this week, Reading Chapter 4: Neural Networks (Mitchell, 1997) See Canvas For subsequent weeks: Scaling Learning Algorithms toward
Convolutional Neural Networks. Srikumar Ramalingam
Convolutional Neural Networks Srikumar Ramalingam Reference Many of the slides are prepared using the following resources: neuralnetworksanddeeplearning.com (mainly Chapter 6) http://cs231n.github.io/convolutional-networks/
EVERYTHING YOU NEED TO KNOW TO BUILD YOUR FIRST CONVOLUTIONAL NEURAL NETWORK (CNN)
EVERYTHING YOU NEED TO KNOW TO BUILD YOUR FIRST CONVOLUTIONAL NEURAL NETWORK (CNN) TARGETED PIECES OF KNOWLEDGE Linear regression Activation function Multi-Layers Perceptron (MLP) Stochastic Gradient Descent
Machine Learning. Neural Networks. (slides from Domingos, Pardo, others)
Machine Learning Neural Networks (slides from Domingos, Pardo, others) Human Brain Neurons Input-Output Transformation Input Spikes Output Spike Spike (= a brief pulse) (Excitatory Post-Synaptic Potential)
Deep learning attracts lots of attention.
Deep Learning Deep learning attracts lots of attention. I believe you have seen lots of exciting results before. Deep learning trends at Google. Source: SIGMOD/Jeff Dean Ups and downs of Deep Learning
Machine Learning. Neural Networks. (slides from Domingos, Pardo, others)
Machine Learning Neural Networks (slides from Domingos, Pardo, others) For this week, Reading Chapter 4: Neural Networks (Mitchell, 1997) See Canvas For subsequent weeks: Scaling Learning Algorithms toward
Feature Design. Feature Design. Feature Design. & Deep Learning
Artificial Intelligence and its applications Lecture 9 & Deep Learning Professor Daniel Yeung danyeung@ieee.org Dr. Patrick Chan patrickchan@ieee.org South China University of Technology, China Appropriately
Deep Learning Lab Course 2017 (Deep Learning Practical)
Deep Learning Lab Course 207 (Deep Learning Practical) Labs: (Computer Vision) Thomas Brox, (Robotics) Wolfram Burgard, (Machine Learning) Frank Hutter, (Neurorobotics) Joschka Boedecker University of
Explaining Predictions of Non-Linear Classifiers in NLP
Explaining Predictions of Non-Linear Classifiers in NLP Leila Arras 1, Franziska Horn 2, Grégoire Montavon 2, Klaus-Robert Müller 2,3, and Wojciech Samek 1 1 Machine Learning Group, Fraunhofer Heinrich
Binary Convolutional Neural Network on RRAM
Binary Convolutional Neural Network on RRAM Tianqi Tang, Lixue Xia, Boxun Li, Yu Wang, Huazhong Yang Dept. of E.E, Tsinghua National Laboratory for Information Science and Technology (TNList) Tsinghua
Modularity Matters: Learning Invariant Relational Reasoning Tasks
Summer Review 3 Modularity Matters: Learning Invariant Relational Reasoning Tasks Jason Jo 1, Vikas Verma 2, Yoshua Bengio 1 1: MILA, Universit de Montral 2: Department of Computer Science Aalto University,
Deep Learning. Hung-yi Lee 李宏毅
Deep Learning Hung-yi Lee 李宏毅 Deep learning attracts lots of attention. I believe you have seen lots of exciting results before. Deep learning trends at Google. Source: SIGMOD 206/Jeff Dean 958: Perceptron
Notes on Adversarial Examples
Notes on Adversarial Examples David Meyer dmm@{1-4-5.net,uoregon.edu,...} March 14, 2017 1 Introduction The surprising discovery of adversarial examples by Szegedy et al. [6] has led to new ways of thinking
CSCI 315: Artificial Intelligence through Deep Learning
CSCI 35: Artificial Intelligence through Deep Learning W&L Fall Term 27 Prof. Levy Convolutional Networks http://wernerstudio.typepad.com/.a/6ad83549adb53ef53629ccf97c-5wi Convolution: Convolution is
Is Robustness the Cost of Accuracy? A Comprehensive Study on the Robustness of 18 Deep Image Classification Models
Is Robustness the Cost of Accuracy? A Comprehensive Study on the Robustness of 18 Deep Image Classification Models Dong Su 1*, Huan Zhang 2*, Hongge Chen 3, Jinfeng Yi 4, Pin-Yu Chen 1, and Yupeng Gao
Axiomatic Attribution of Neural Networks
Axiomatic Attribution of Neural Networks Mukund Sundararajan* 1, Ankur Taly* 1, Qiqi Yan* 1 1 Google Inc. Presenter: Arshdeep Sekhon Mukund Sundararajan*, Ankur Taly*, Qiqi Yan*Axiomatic Attribution of
Explaining Predictions of Non-Linear Classifiers in NLP
Explaining Predictions of Non-Linear Classifiers in NLP Leila Arras 1, Franziska Horn 2, Grégoire Montavon 2, Klaus-Robert Müller 2,3, and Wojciech Samek 1 1 Machine Learning Group, Fraunhofer Heinrich
Lecture 14: Deep Generative Learning
Generative Modeling CSED703R: Deep Learning for Visual Recognition (2017F) Lecture 14: Deep Generative Learning Density estimation Reconstructing probability density function using samples Bohyung Han
Deep Learning. Convolutional Neural Network (CNNs) Ali Ghodsi. October 30, Slides are partially based on Book in preparation, Deep Learning
Convolutional Neural Network (CNNs) University of Waterloo October 30, 2015 Slides are partially based on Book in preparation, by Bengio, Goodfellow, and Aaron Courville, 2015 Convolutional Networks Convolutional
COMPARING FIXED AND ADAPTIVE COMPUTATION TIME FOR RE-
Workshop track - ICLR COMPARING FIXED AND ADAPTIVE COMPUTATION TIME FOR RE- CURRENT NEURAL NETWORKS Daniel Fojo, Víctor Campos, Xavier Giró-i-Nieto Universitat Politècnica de Catalunya, Barcelona Supercomputing
Deep Learning: Pre- Requisites. Understanding gradient descent, autodiff, and softmax
Deep Learning: Pre- Requisites Understanding gradient descent, autodiff, and softmax Gradient Descent autodiff Gradient descent requires knowledge of, well, the gradient from your cost function (MSE) Mathematically
Towards Accurate Binary Convolutional Neural Network
Paper: #261 Poster: Pacific Ballroom #101 Towards Accurate Binary Convolutional Neural Network Xiaofan Lin, Cong Zhao and Wei Pan* firstname.lastname@dji.com Photos and videos are either original work
Final Examination CS540-2: Introduction to Artificial Intelligence
Final Examination CS540-2: Introduction to Artificial Intelligence May 9, 2018 LAST NAME: SOLUTIONS FIRST NAME: Directions 1. This exam contains 33 questions worth a total of 100 points 2. Fill in your
@SoyGema GEMA PARREÑO PIQUERAS
@SoyGema GEMA PARREÑO PIQUERAS WHAT IS AN ARTIFICIAL NEURON? WHAT IS AN ARTIFICIAL NEURON? Image Recognition Classification using Softmax Regressions and Convolutional Neural Networks Languaje Understanding
(Feed-Forward) Neural Networks Dr. Hajira Jabeen, Prof. Jens Lehmann
(Feed-Forward) Neural Networks 2016-12-06 Dr. Hajira Jabeen, Prof. Jens Lehmann Outline In the previous lectures we have learned about tensors and factorization methods. RESCAL is a bilinear model for
Introduction To Artificial Neural Networks
Introduction To Artificial Neural Networks Machine Learning Supervised circle square circle square Unsupervised group these into two categories Supervised Machine Learning Supervised Machine Learning Supervised
Handwritten Indic Character Recognition using Capsule Networks
Handwritten Indic Character Recognition using Capsule Networks Bodhisatwa Mandal,Suvam Dubey, Swarnendu Ghosh, RiteshSarkhel, Nibaran Das Dept. of CSE, Jadavpur University, Kolkata, 700032, WB, India.