Lecture 11-1 CNN introduction. Sung Kim
|
|
|
- Branden Bryan
- 6 years ago
- Views:
Transcription
1 Lecture 11-1 CNN introduction Sung Kim
2 'The only limit is your imagination'
3 Lecture 7: Convolutional Neural Networks Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-1
4 A bit of history: Hubel & Wiesel, 1959 RECEPTIVE FIELDS OF SINGLE NEURONES IN THE CAT'S STRIATE CORTEX 1962 RECEPTIVE FIELDS, BINOCULAR INTERACTION AND FUNCTIONAL ARCHITECTURE IN THE CAT'S VISUAL CORTEX Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-7
5 preview: Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-22
6 Start with an image (width x hight x depth) 32x32x3 image
7 32x32x3 image Let s focus on a small area only
8 Let s focus on a small area only (5x5x3) 32x32x3 image 5x5x3 filter
9 Get one number using the filter one number! 32x32x3 image
10 Get one number using the filter one number! 5x5x3 filter =Wx+b =ReLU(Wx+b) 32x32x3 image
11 Let s look at other areas with the same filter (w) one number! 32x32x3 image
12 Let s look at other areas with the same filter (w) one number! 32x32x3 image
13 Let s look at other areas with the same filter (w) one number! 32x32x3 image
14 Let s look at other areas with the same filter (w) one number! 32x32x3 image
15 Let s look at other areas with the same filter (w) one number! How many numbers can we get? 32x32x3 image
16 A closer look at spatial dimensions: 7 7x7 input (spatially) assume 3x3 filter 7 Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-24
17 A closer look at spatial dimensions: 7 7x7 input (spatially) assume 3x3 filter 7 Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-25
18 A closer look at spatial dimensions: 7 7x7 input (spatially) assume 3x3 filter 7 Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-26
19 A closer look at spatial dimensions: 7 7x7 input (spatially) assume 3x3 filter 7 Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-27
20 A closer look at spatial dimensions: 7 7x7 input (spatially) assume 3x3 filter 7 => 5x5 output Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-28
21 A closer look at spatial dimensions: 7 7x7 input (spatially) assume 3x3 filter applied with stride 2 7 Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-29
22 A closer look at spatial dimensions: 7 7x7 input (spatially) assume 3x3 filter applied with stride 2 7 Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-30
23 A closer look at spatial dimensions: 7 7 7x7 input (spatially) assume 3x3 filter applied with stride 2 => 3x3 output! Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-31
24 F N F N Output size: (N - F) / stride + 1 e.g. N = 7, F = 3: stride 1 => (7-3)/1 + 1 = 5 stride 2 => (7-3)/2 + 1 = 3 stride 3 => (7-3)/3 + 1 = 2.33 :\ Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-34
25 In practice: Common to zero pad the border e.g. input 7x7 3x3 filter, applied with stride 1 pad with 1 pixel border => what is the output? 0 0 (recall:) (N - F) / stride + 1 Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-35
26 In practice: Common to zero pad the border e.g. input 7x7 3x3 filter, applied with stride 1 pad with 1 pixel border => what is the output? 7x7 output! Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-36
27 In practice: Common to zero pad the border e.g. input 7x7 3x3 filter, applied with stride 1 pad with 1 pixel border => what is the output? 7x7 output! in general, common to see CONV layers with stride 1, filters of size FxF, and zero-padding with (F-1)/2. (will preserve size spatially) e.g. F = 3 => zero pad with 1 F = 5 => zero pad with 2 F = 7 => zero pad with 3 Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-37
28 Swiping the entire image 5x5x3 filter 1 32x32x3 image
29 Swiping the entire image 5x5x3 filter 2 32x32x3 image
30 Swiping the entire image 6 filters (5x5x3) activation maps (?,?,?) 32x32x3 image
31 32x32x3 image Convolution layers
32 32x32x3 image Convolution layers
33 32x32x3 image Convolution layers How many weight variables? How to set them?
![Preview [From recent Yann LeCun slides] Fei-Fei](/docs-images/80/81108430/images/34-0.jpg "Li & Andrej Karpathy & Justin Johnson Lecture")
34 Preview [From recent Yann LeCun slides] Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-19
35 preview: Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-22
36 Lecture 11-2 CNN introduction: Max pooling and others Sung Kim
37 preview: Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-22
38 conv layer Pooling layer (sampling)
39 Pooling layer (sampling) conv layer resize (sampling)
40 conv layer Pooling layer (sampling)
41 MAX POOLING x Single depth slice max pool with 2x2 filters and stride y Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-55
42 MAX POOLING x Single depth slice max pool with 2x2 filters and stride y Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-55
43 Fully Connected Layer (FC layer) - Contains neurons that connect to the entire input volume, as in ordinary Neural Networks Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-58
44 [ConvNetJS demo: training on CIFAR-10] Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-59
45 Lecture 11-3 CNN case study Sung Kim
46 Lecture 7: Convolutional Neural Networks Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-1
47 Case Study: LeNet-5 [LeCun et al., 1998] Conv filters were 5x5, applied at stride 1 Subsampling (Pooling) layers were 2x2 applied at stride 2 i.e. architecture is [CONV-POOL-CONV-POOL-CONV-FC] Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-60
48 Case Study: AlexNet [Krizhevsky et al. 2012] Input: 227x227x3 images First layer (CONV1): 96 11x11 filters applied at stride 4 => Output volume [55x55x96] Parameters: (11*11*3)*96 = 35K Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-63
49 Case Study: AlexNet [Krizhevsky et al. 2012] Input: 227x227x3 images After CONV1: 55x55x96 Second layer (POOL1): 3x3 filters applied at stride 2 Output volume: 27x27x96 Parameters: 0! Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-66
50 Case Study: AlexNet [Krizhevsky et al. 2012] Input: 227x227x3 images After CONV1: 55x55x96 After POOL1: 27x27x96... Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-67
51 Case Study: AlexNet [Krizhevsky et al. 2012] Full (simplified) AlexNet architecture: [227x227x3] INPUT [55x55x96] CONV1: 96 11x11 filters at stride 4, pad 0 [27x27x96] MAX POOL1: 3x3 filters at stride 2 [27x27x96] NORM1: Normalization layer [27x27x256] CONV2: 256 5x5 filters at stride 1, pad 2 [13x13x256] MAX POOL2: 3x3 filters at stride 2 [13x13x256] NORM2: Normalization layer [13x13x384] CONV3: 384 3x3 filters at stride 1, pad 1 [13x13x384] CONV4: 384 3x3 filters at stride 1, pad 1 [13x13x256] CONV5: 256 3x3 filters at stride 1, pad 1 [6x6x256] MAX POOL3: 3x3 filters at stride 2 [4096] FC6: 4096 neurons [4096] FC7: 4096 neurons [1000] FC8: 1000 neurons (class scores) Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-68
52 Case Study: AlexNet [Krizhevsky et al. 2012] Full (simplified) AlexNet architecture: [227x227x3] INPUT [55x55x96] CONV1: 96 11x11 filters at stride 4, pad 0 [27x27x96] MAX POOL1: 3x3 filters at stride 2 [27x27x96] NORM1: Normalization layer [27x27x256] CONV2: 256 5x5 filters at stride 1, pad 2 [13x13x256] MAX POOL2: 3x3 filters at stride 2 [13x13x256] NORM2: Normalization layer [13x13x384] CONV3: 384 3x3 filters at stride 1, pad 1 [13x13x384] CONV4: 384 3x3 filters at stride 1, pad 1 [13x13x256] CONV5: 256 3x3 filters at stride 1, pad 1 [6x6x256] MAX POOL3: 3x3 filters at stride 2 [4096] FC6: 4096 neurons [4096] FC7: 4096 neurons [1000] FC8: 1000 neurons (class scores) Details/Retrospectives: - first use of ReLU - used Norm layers (not common anymore) - heavy data augmentation - dropout batch size SGD Momentum Learning rate 1e-2, reduced by 10 manually when val accuracy plateaus - L2 weight decay 5e-4-7 CNN ensemble: 18.2% -> 15.4% Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-69
53 Case Study: GoogLeNet [Szegedy et al., 2014] Inception module ILSVRC 2014 winner (6.7% top 5 error) Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-75
54 Case Study: ResNet [He et al., 2015] ILSVRC 2015 winner (3.6% top 5 error) Slide from Kaiming He s recent presentation Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-77
55 Case Study: ResNet [He et al., 2015] ILSVRC 2015 winner (3.6% top 5 error) 2-3 weeks of training on 8 GPU machine at runtime: faster than a VGGNet! (even though it has 8x more layers) (slide from Kaiming He s recent presentation) Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-80
56 Case Study: ResNet [He et al., 2015] 224x224x3 spatial dimension only 56x56! Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-81
57 Case Study: ResNet [He et al., 2015] Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-82
58 Case Study: ResNet [He et al., 2015] (this trick is also used in GoogLeNet) Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-85
59 Convolutional Neural Networks for Sentence Classification [Yoon Kim, 2014]
60 Case Study Bonus: DeepMind s AlphaGo Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-87
![policy network: [19x19x48] Input CONV1: 192 5x5 filters, stride 1, pad 2 => [19x19x192] CONV2.](/docs-images/80/81108430/images/61-0.jpg ".12: 192 3x3 filters, stride 1, pad 1 => [19x19x192] CONV: 1 1x1 filter, stride 1, pad 0 => [19x19] (probability map of promising moves) Fei-Fei")
61 policy network: [19x19x48] Input CONV1: 192 5x5 filters, stride 1, pad 2 => [19x19x192] CONV2..12: 192 3x3 filters, stride 1, pad 1 => [19x19x192] CONV: 1 1x1 filter, stride 1, pad 0 => [19x19] (probability map of promising moves) Fei-Fei Li & Andrej Karpathy & Justin Johnson Lecture 7-88
62 'The only limit is your imagination'
63 Next Recurrent Neural Nets (RNN)
Deep Learning. Dr. Johan Hagelbäck.
Deep Learning Dr. Johan Hagelbäck johan.hagelback@lnu.se http://aiguy.org Image Classification Image classification can be a difficult task Some of the challenges we have to face are: Viewpoint variation:
Convolutional Neural Networks. Fei-Fei Li & Justin Johnson & Serena Yeung. Lecture 5-1
Lecture 5: Convolutional Neural Networks Lecture 5-1 Administrative Assignment 1 due Thursday April 20, 11:59pm on Canvas Assignment 2 will be released Thursday Lecture 5-2 Last time: Neural Networks Linear
Convolutional Neural Networks. Fei-Fei Li & Justin Johnson & Serena Yeung. Lecture 5-1
Lecture 5: Convolutional Neural Networks Lecture 5-1 Administrative Assignment 1 due Wednesday April 17, 11:59pm - Important: tag your solutions with the corresponding hw question in gradescope! - Some
Biologically Inspired Computation
Biologically Inspired Computation Deep Learning & Convolutional Neural Networks Joe Marino biologically inspired computation biological intelligence flexible capable of detecting/ executing/reasoning about
Convolutional Neural Networks
Convolutional Neural Networks Convolution, LeNet, AlexNet, VGGNet, GoogleNet, Resnet, DenseNet, CAM, Deconvolution Sept 17, 2018 Aaditya Prakash Convolution Convolution Demo Convolution Convolution in
Impact of Automatic Feature Extraction in Deep Learning Architecture
Impact of Automatic Feature Extraction in Deep Learning Architecture Fatma Shaheen, Brijesh Verma and Md Asafuddoula Centre for Intelligent Systems Central Queensland University, Brisbane, Australia {f.shaheen,
Introduction to Machine Learning
Introduction to Machine Learning Deep Learning Barnabás Póczos Credits Many of the pictures, results, and other materials are taken from: Ruslan Salakhutdinov Joshua Bengio Geoffrey Hinton Yann LeCun 2
CS 7643: Deep Learning
CS 7643: Deep Learning Topics: Toeplitz matrices and convolutions = matrix-mult Dilated/a-trous convolutions Backprop in conv layers Transposed convolutions Dhruv Batra Georgia Tech HW1 extension 09/22
Convolu'onal Neural Networks. November 17, 2015
Convolu'onal Neural Networks November 17, 2015 Ar'ficial Neural Networks Feedforward neural networks Ar'ficial Neural Networks Feedforward, fully-connected neural networks Ar'ficial Neural Networks Feedforward,
یادآوری: خالصه CNN. ConvNet
1 ConvNet یادآوری: خالصه CNN شبکه عصبی کانولوشنال یا Convolutional Neural Networks یا نوعی از شبکههای عصبی عمیق مدل یادگیری آن باناظر.اصالح وزنها با الگوریتم back-propagation مناسب برای داده های حجیم و
Lesson 08. Convolutional Neural Network. Ing. Marek Hrúz, Ph.D. Katedra Kybernetiky Fakulta aplikovaných věd Západočeská univerzita v Plzni.
Lesson 08 Convolutional Neural Network Ing. Marek Hrúz, Ph.D. Katedra Kybernetiky Fakulta aplikovaných věd Západočeská univerzita v Plzni Lesson 08 Convolution we will consider 2D convolution the result
Lecture 23 Deep Learning: Segmentation
Lecture 23 Deep Learning: Segmentation COS 429: Computer Vision Thanks: most of these slides shamelessly adapted from Stanford CS231n: Convolutional Neural Networks for Visual Recognition Fei-Fei Li, Andrej
CONVOLUTIONAL NEURAL NETWORKS: MOTIVATION, CONVOLUTION OPERATION, ALEXNET
CONVOLUTIONAL NEURAL NETWORKS: MOTIVATION, CONVOLUTION OPERATION, ALEXNET MOTIVATION Fully connected neural network Example 1000x1000 image 1M hidden units 10 12 (= 10 6 10 6 ) parameters! Observation
What Is And How Will Machine Learning Change Our Lives. Fair Use Agreement
What Is And How Will Machine Learning Change Our Lives Raymond Ptucha, Rochester Institute of Technology 2018 Engineering Symposium April 24, 2018, 9:45am Ptucha 18 1 Fair Use Agreement This agreement
EE-559 Deep learning 7.2. Networks for image classification
EE-559 Deep learning 7.2. Networks for image classification François Fleuret https://fleuret.org/ee559/ Fri Nov 16 22:58:34 UTC 2018 ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNE Image classification, standard
Detection and Segmentation. Fei-Fei Li & Justin Johnson & Serena Yeung. Lecture 11 -
Lecture 11: Detection and Segmentation Lecture 11-1 May 10, 2017 Administrative Midterms being graded Please don t discuss midterms until next week - some students not yet taken A2 being graded Project
PROJECT REPORT. Using Deep Learning to Classify Malignancy Associated Changes
Using Deep Learning to Classify Malignancy Associated Changes Hakan Wieslander, Gustav Forslid Project in Computational Science: Report January 2017 PROJECT REPORT Department of Information Technology
Coursework 2. MLP Lecture 7 Convolutional Networks 1
Coursework 2 MLP Lecture 7 Convolutional Networks 1 Coursework 2 - Overview and Objectives Overview: Use a selection of the techniques covered in the course so far to train accurate multi-layer networks
LANDMARK recognition is an important feature for
1 NU-LiteNet: Mobile Landmark Recognition using Convolutional Neural Networks Chakkrit Termritthikun, Surachet Kanprachar, Paisarn Muneesawang arxiv:1810.01074v1 [cs.cv] 2 Oct 2018 Abstract The growth
6. Convolutional Neural Networks
6. Convolutional Neural Networks CS 519 Deep Learning, Winter 2016 Fuxin Li With materials from Zsolt Kira Quiz coming up Next Tuesday (1/26) 15 minutes Topics: Optimization Basic neural networks No Convolutional
arxiv: v1 [cs.ce] 9 Jan 2018
![arxiv: v1 [cs.ce] 9 Jan 2018](/thumbs/77/76232406.jpg "arxiv: v1 [cs.ce] 9 Jan 2018")
Predict Forex Trend via Convolutional Neural Networks Yun-Cheng Tsai, 1 Jun-Hao Chen, 2 Jun-Jie Wang 3 arxiv:1801.03018v1 [cs.ce] 9 Jan 2018 1 Center for General Education 2,3 Department of Computer Science
Camera Model Identification With The Use of Deep Convolutional Neural Networks
Camera Model Identification With The Use of Deep Convolutional Neural Networks Amel TUAMA 2,3, Frédéric COMBY 2,3, and Marc CHAUMONT 1,2,3 (1) University of Nîmes, France (2) University Montpellier, France
Research on Hand Gesture Recognition Using Convolutional Neural Network
Research on Hand Gesture Recognition Using Convolutional Neural Network Tian Zhaoyang a, Cheng Lee Lung b a Department of Electronic Engineering, City University of Hong Kong, Hong Kong, China E-mail address:
Convolutional Networks Overview
Convolutional Networks Overview Sargur Srihari 1 Topics Limitations of Conventional Neural Networks The convolution operation Convolutional Networks Pooling Convolutional Network Architecture Advantages
En ny æra for uthenting av informasjon fra satellittbilder ved hjelp av maskinlæring
En ny æra for uthenting av informasjon fra satellittbilder ved hjelp av maskinlæring Mathilde Ørstavik og Terje Midtbø Mathilde Ørstavik and Terje Midtbø, A New Era for Feature Extraction in Remotely Sensed
Vehicle Color Recognition using Convolutional Neural Network
Vehicle Color Recognition using Convolutional Neural Network Reza Fuad Rachmadi and I Ketut Eddy Purnama Multimedia and Network Engineering Department, Institut Teknologi Sepuluh Nopember, Keputih Sukolilo,
arxiv: v2 [cs.cv] 11 Oct 2016
![arxiv: v2 [cs.cv] 11 Oct 2016](/thumbs/94/119169670.jpg "arxiv: v2 [cs.cv] 11 Oct 2016")
Xception: Deep Learning with Depthwise Separable Convolutions arxiv:1610.02357v2 [cs.cv] 11 Oct 2016 François Chollet Google, Inc. fchollet@google.com Monday 10 th October, 2016 Abstract We present an
Lecture 17 Convolutional Neural Networks
Lecture 17 Convolutional Neural Networks 30 March 2016 Taylor B. Arnold Yale Statistics STAT 365/665 1/22 Notes: Problem set 6 is online and due next Friday, April 8th Problem sets 7,8, and 9 will be due
Visualizing and Understanding. Fei-Fei Li & Justin Johnson & Serena Yeung. Lecture 12 -
Lecture 12: Visualizing and Understanding Lecture 12-1 May 16, 2017 Administrative Milestones due tonight on Canvas, 11:59pm Midterm grades released on Gradescope this week A3 due next Friday, 5/26 HyperQuest
Xception: Deep Learning with Depthwise Separable Convolutions
Xception: Deep Learning with Depthwise Separable Convolutions François Chollet Google, Inc. fchollet@google.com 1 A variant of the process is to independently look at width-wise correarxiv:1610.02357v3
An Introduction to Convolutional Neural Networks. Alessandro Giusti Dalle Molle Institute for Artificial Intelligence Lugano, Switzerland
An Introduction to Convolutional Neural Networks Alessandro Giusti Dalle Molle Institute for Artificial Intelligence Lugano, Switzerland Sources & Resources - Andrej Karpathy, CS231n http://cs231n.github.io/convolutional-networks/
arxiv: v5 [cs.cv] 23 Aug 2017
![arxiv: v5 [cs.cv] 23 Aug 2017](/thumbs/83/88579271.jpg "arxiv: v5 [cs.cv] 23 Aug 2017")
DelugeNets: Deep Networks with Efficient and Flexible Cross-layer Information Inflows arxiv:111.555v5 [cs.cv] 3 Aug 17 Jason Kuen 1 jkuen1@ntu.edu.sg Xiangfei Kong 1 xfkong@ntu.edu.sg Gang Wang gangwang@gmail.com
clcnet: Improving the Efficiency of Convolutional Neural Network using Channel Local Convolutions
clcnet: Improving the Efficiency of Convolutional Neural Network using Channel Local Convolutions Dong-Qing Zhang ImaginationAI LLC dongqing@gmail.com Abstract Depthwise convolution and grouped convolution
Tiny ImageNet Challenge Investigating the Scaling of Inception Layers for Reduced Scale Classification Problems
Tiny ImageNet Challenge Investigating the Scaling of Inception Layers for Reduced Scale Classification Problems Emeric Stéphane Boigné eboigne@stanford.edu Jan Felix Heyse heyse@stanford.edu Abstract Scaling
ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions
ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions Hongyang Gao Texas A&M University College Station, TX hongyang.gao@tamu.edu Zhengyang Wang Texas A&M University
arxiv: v1 [cs.cv] 15 Apr 2016
![arxiv: v1 [cs.cv] 15 Apr 2016](/thumbs/80/81898948.jpg "arxiv: v1 [cs.cv] 15 Apr 2016")
High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks arxiv:1604.04339v1 [cs.cv] 15 Apr 2016 Zifeng Wu, Chunhua Shen, Anton van den Hengel The University of Adelaide, SA 5005,
Deep Learning Basics Lecture 9: Recurrent Neural Networks. Princeton University COS 495 Instructor: Yingyu Liang
Deep Learning Basics Lecture 9: Recurrent Neural Networks Princeton University COS 495 Instructor: Yingyu Liang Introduction Recurrent neural networks Dates back to (Rumelhart et al., 1986) A family of
Automatic point-of-interest image cropping via ensembled convolutionalization
1 Automatic point-of-interest image cropping via ensembled convolutionalization Andrea Asperti and Pietro Battilana University of Bologna Department of informatics: Science and Engineering (DISI) Abstract
CSC 578 Neural Networks and Deep Learning
CSC 578 Neural Networks and Deep Learning Fall 2018/19 6. Convolutional Neural Networks (Some figures adapted from NNDL book) 1 Convolution Neural Networks 1. Convolutional Neural Networks Convolution,
Convolutional neural networks
Convolutional neural networks Themes Curriculum: Ch 9.1, 9.2 and http://cs231n.github.io/convolutionalnetworks/ The simple motivation and idea How it s done Receptive field Pooling Dilated convolutions
A Vision Based Hand Gesture Recognition System using Convolutional Neural Networks
A Vision Based Hand Gesture Recognition System using Convolutional Neural Networks Simran Shah 1, Ami Kotia 2, Kausha Nisar 3, Aneri Udeshi 4, Prof. Pramila. M. Chawan 5 1,2,3,4U.G. Students, Department
Classification Accuracies of Malaria Infected Cells Using Deep Convolutional Neural Networks Based on Decompressed Images
Classification Accuracies of Malaria Infected Cells Using Deep Convolutional Neural Networks Based on Decompressed Images Yuhang Dong, Zhuocheng Jiang, Hongda Shen, W. David Pan Dept. of Electrical & Computer
Free-hand Sketch Recognition Classification
Free-hand Sketch Recognition Classification Wayne Lu Stanford University waynelu@stanford.edu Elizabeth Tran Stanford University eliztran@stanford.edu Abstract People use sketches to express and record
Image Manipulation Detection using Convolutional Neural Network
Image Manipulation Detection using Convolutional Neural Network Dong-Hyun Kim 1 and Hae-Yeoun Lee 2,* 1 Graduate Student, 2 PhD, Professor 1,2 Department of Computer Software Engineering, Kumoh National
Fully Convolutional Networks for Semantic Segmentation
Fully Convolutional Networks for Semantic Segmentation Jonathan Long* Evan Shelhamer* Trevor Darrell UC Berkeley Presented by: Gordon Christie 1 Overview Reinterpret standard classification convnets as
Sketch-a-Net that Beats Humans
Sketch-a-Net that Beats Humans Qian Yu SketchLab@QMUL Queen Mary University of London 1 Authors Qian Yu Yongxin Yang Yi-Zhe Song Tao Xiang Timothy Hospedales 2 Let s play a game! Round 1 Easy fish face
Synthetic View Generation for Absolute Pose Regression and Image Synthesis: Supplementary material
Synthetic View Generation for Absolute Pose Regression and Image Synthesis: Supplementary material Pulak Purkait 1 pulak.cv@gmail.com Cheng Zhao 2 irobotcheng@gmail.com Christopher Zach 1 christopher.m.zach@gmail.com
A Fuller Understanding of Fully Convolutional Networks. Evan Shelhamer* Jonathan Long* Trevor Darrell UC Berkeley in CVPR'15, PAMI'16
A Fuller Understanding of Fully Convolutional Networks Evan Shelhamer* Jonathan Long* Trevor Darrell UC Berkeley in CVPR'15, PAMI'16 1 pixels in, pixels out colorization Zhang et al.2016 monocular depth
An energy-efficient coarse grained spatial architecture for convolutional neural networks AlexNet
LETTER IEICE Electronics Express, Vol.14, No.15, 1 12 An energy-efficient coarse grained spatial architecture for convolutional neural networks AlexNet Boya Zhao a), Mingjiang Wang b), and Ming Liu Harbin
GPU ACCELERATED DEEP LEARNING WITH CUDNN
GPU ACCELERATED DEEP LEARNING WITH CUDNN Larry Brown Ph.D. March 2015 AGENDA 1 Introducing cudnn and GPUs 2 Deep Learning Context 3 cudnn V2 4 Using cudnn 2 Introducing cudnn and GPUs 3 HOW GPU ACCELERATION
Neural Network Part 4: Recurrent Neural Networks
Neural Network Part 4: Recurrent Neural Networks Yingyu Liang Computer Sciences 760 Fall 2017 http://pages.cs.wisc.edu/~yliang/cs760/ Some of the slides in these lectures have been adapted/borrowed from
ON CLASSIFICATION OF DISTORTED IMAGES WITH DEEP CONVOLUTIONAL NEURAL NETWORKS. Yiren Zhou, Sibo Song, Ngai-Man Cheung
ON CLASSIFICATION OF DISTORTED IMAGES WITH DEEP CONVOLUTIONAL NEURAL NETWORKS Yiren Zhou, Sibo Song, Ngai-Man Cheung Singapore University of Technology and Design In this section, we briefly introduce
ROAD RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS
Bulletin of the Transilvania University of Braşov Vol. 10 (59) No. 2-2017 Series I: Engineering Sciences ROAD RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS E. HORVÁTH 1 C. POZNA 2 Á. BALLAGI 3
SIMULATION-BASED MODEL CONTROL USING STATIC HAND GESTURES IN MATLAB
SIMULATION-BASED MODEL CONTROL USING STATIC HAND GESTURES IN MATLAB S. Kajan, J. Goga Institute of Robotics and Cybernetics, Faculty of Electrical Engineering and Information Technology, Slovak University
Compact Deep Convolutional Neural Networks for Image Classification
1 Compact Deep Convolutional Neural Networks for Image Classification Zejia Zheng, Zhu Li, Abhishek Nagar 1 and Woosung Kang 2 Abstract Convolutional Neural Network is efficient in learning hierarchical
INFORMATION about image authenticity can be used in
1 Constrained Convolutional Neural Networs: A New Approach Towards General Purpose Image Manipulation Detection Belhassen Bayar, Student Member, IEEE, and Matthew C. Stamm, Member, IEEE Abstract Identifying
Semantic Segmentation on Resource Constrained Devices
Semantic Segmentation on Resource Constrained Devices Sachin Mehta University of Washington, Seattle In collaboration with Mohammad Rastegari, Anat Caspi, Linda Shapiro, and Hannaneh Hajishirzi Project
ECS 289G UC Davis Paper Presenta6on #1
ECS 289G UC Davis Paper Presenta6on #1 ImageNet Classifica6on with Deep Convolu6onal Neural Networks Mohammad Motamedi Mohammad Motamedi ECS 289G PAPER PRESENTATION - UC DAVIS 1 Convolu6onal Neural Networks
Wide Residual Networks
SERGEY ZAGORUYKO AND NIKOS KOMODAKIS: WIDE RESIDUAL NETWORKS 1 Wide Residual Networks Sergey Zagoruyko sergey.zagoruyko@enpc.fr Nikos Komodakis nikos.komodakis@enpc.fr Université Paris-Est, École des Ponts
GESTURE RECOGNITION WITH 3D CNNS
April 4-7, 2016 Silicon Valley GESTURE RECOGNITION WITH 3D CNNS Pavlo Molchanov Xiaodong Yang Shalini Gupta Kihwan Kim Stephen Tyree Jan Kautz 4/6/2016 Motivation AGENDA Problem statement Selecting the
arxiv: v4 [cs.cv] 14 Jun 2017
![arxiv: v4 [cs.cv] 14 Jun 2017](/thumbs/74/69658497.jpg "arxiv: v4 [cs.cv] 14 Jun 2017")
SERGEY ZAGORUYKO AND NIKOS KOMODAKIS: WIDE RESIDUAL NETWORKS 1 arxiv:1605.07146v4 [cs.cv] 14 Jun 2017 Wide Residual Networks Sergey Zagoruyko sergey.zagoruyko@enpc.fr Nikos Komodakis nikos.komodakis@enpc.fr
arxiv: v1 [cs.cv] 23 May 2016
![arxiv: v1 [cs.cv] 23 May 2016](/thumbs/71/66054425.jpg "arxiv: v1 [cs.cv] 23 May 2016")
arxiv:1605.07146v1 [cs.cv] 23 May 2016 SERGEY ZAGORUYKO AND NIKOS KOMODAKIS: WIDE RESIDUAL NETWORKS 1 Wide Residual Networks Sergey Zagoruyko sergey.zagoruyko@enpc.fr Nikos Komodakis nikos.komodakis@enpc.fr
Analyzing features learned for Offline Signature Verification using Deep CNNs
Accepted as a conference paper for ICPR 2016 Analyzing features learned for Offline Signature Verification using Deep CNNs Luiz G. Hafemann, Robert Sabourin Lab. d imagerie, de vision et d intelligence
Introduction to Machine Learning
Introduction to Machine Learning Perceptron Barnabás Póczos Contents History of Artificial Neural Networks Definitions: Perceptron, Multi-Layer Perceptron Perceptron algorithm 2 Short History of Artificial
Learning Deep Networks from Noisy Labels with Dropout Regularization
Learning Deep Networks from Noisy Labels with Dropout Regularization Ishan Jindal*, Matthew Nokleby*, Xuewen Chen** *Department of Electrical and Computer Engineering **Department of Computer Science Wayne
ECE 599/692 Deep Learning Lecture 19 Beyond BP and CNN
ECE 599/692 Deep Learning Lecture 19 Beyond BP and CNN Hairong Qi, Gonzalez Family Professor Electrical Engineering and Computer Science University of Tennessee, Knoxville http://www.eecs.utk.edu/faculty/qi
Can you tell a face from a HEVC bitstream?
Can you tell a face from a HEVC bitstream? Saeed Ranjbar Alvar, Hyomin Choi and Ivan V. Bajić School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada Email: {saeedr,chyomin, ibajic}@sfu.ca
Automatic tumor segmentation in breast ultrasound images using a dilated fully convolutional network combined with an active contour model
Automatic tumor segmentation in breast ultrasound images using a dilated fully convolutional network combined with an active contour model Yuzhou Hu Departmentof Electronic Engineering, Fudan University,
Automated Image Timestamp Inference Using Convolutional Neural Networks
Automated Image Timestamp Inference Using Convolutional Neural Networks Prafull Sharma prafull7@stanford.edu Michel Schoemaker michel92@stanford.edu Stanford University David Pan napdivad@stanford.edu
Deformable Convolutional Networks
Deformable Convolutional Networks Jifeng Dai^ With Haozhi Qi*^, Yuwen Xiong*^, Yi Li*^, Guodong Zhang*^, Han Hu, Yichen Wei Visual Computing Group Microsoft Research Asia (* interns at MSRA, ^ equal contribution)
A Deep Learning Approach To Universal Image Manipulation Detection Using A New Convolutional Layer
A Deep Learning Approach To Universal Image Manipulation Detection Using A New Convolutional Layer ABSTRACT Belhassen Bayar Drexel University Dept. of ECE Philadelphia, PA, USA bb632@drexel.edu When creating
Comparison of Google Image Search and ResNet Image Classification Using Image Similarity Metrics
University of Arkansas, Fayetteville ScholarWorks@UARK Computer Science and Computer Engineering Undergraduate Honors Theses Computer Science and Computer Engineering 5-2018 Comparison of Google Image
CPSC 340: Machine Learning and Data Mining. Convolutional Neural Networks Fall 2018
CPSC 340: Machine Learning and Data Mining Convolutional Neural Networks Fall 2018 Admin Mike and I finish CNNs on Wednesday. After that, we will cover different topics: Mike will do a demo of training
Recognition: Overview. Sanja Fidler CSC420: Intro to Image Understanding 1/ 83
Recognition: Overview Sanja Fidler CSC420: Intro to Image Understanding 1/ 83 Textbook This book has a lot of material: K. Grauman and B. Leibe Visual Object Recognition Synthesis Lectures On Computer
Multi-frame convolutional neural networks for object detection in temporal data
Calhoun: The NPS Institutional Archive DSpace Repository Theses and Dissertations Thesis and Dissertation Collection 2017-03 Multi-frame convolutional neural networks for object detection in temporal data
arxiv: v1 [cs.cv] 28 Nov 2017 Abstract
![arxiv: v1 [cs.cv] 28 Nov 2017 Abstract](/thumbs/86/93950533.jpg "arxiv: v1 [cs.cv] 28 Nov 2017 Abstract")
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks Zhaofan Qiu, Ting Yao, and Tao Mei University of Science and Technology of China, Hefei, China Microsoft Research, Beijing, China
Convolutional Neural Network-based Steganalysis on Spatial Domain
Convolutional Neural Network-based Steganalysis on Spatial Domain Dong-Hyun Kim, and Hae-Yeoun Lee Abstract Steganalysis has been studied to detect the existence of hidden messages by steganography. However,
Google DeepMind s AlphaGo vs. world Go champion Lee Sedol
Google DeepMind s AlphaGo vs. world Go champion Lee Sedol Review of Nature paper: Mastering the game of Go with Deep Neural Networks & Tree Search Tapani Raiko Thanks to Antti Tarvainen for some slides
Learning Pixel-Distribution Prior with Wider Convolution for Image Denoising
Learning Pixel-Distribution Prior with Wider Convolution for Image Denoising Peng Liu University of Florida pliu1@ufl.edu Ruogu Fang University of Florida ruogu.fang@bme.ufl.edu arxiv:177.9135v1 [cs.cv]
NU-Net: Deep Residual Wide Field of View Convolutional Neural Network for Semantic Segmentation
NU-Net: Deep Residual Wide Field of View Convolutional Neural Network for Semantic Segmentation Mohamed Samy 1 Karim Amer 1 Kareem Eissa Mahmoud Shaker Mohamed ElHelw Center for Informatics Science Nile
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks Zhaofan Qiu, Ting Yao, and Tao Mei University of Science and Technology of China, Hefei, China Microsoft Research, Beijing, China
Understanding Neural Networks : Part II
TensorFlow Workshop 2018 Understanding Neural Networks Part II : Convolutional Layers and Collaborative Filters Nick Winovich Department of Mathematics Purdue University July 2018 Outline 1 Convolutional
Correlating Filter Diversity with Convolutional Neural Network Accuracy
Correlating Filter Diversity with Convolutional Neural Network Accuracy Casey A. Graff School of Computer Science and Engineering University of California San Diego La Jolla, CA 92023 Email: cagraff@ucsd.edu
Pelee: A Real-Time Object Detection System on Mobile Devices
Pelee: A Real-Time Object Detection System on Mobile Devices Robert J. Wang, Xiang Li, Shuang Ao & Charles X. Ling Department of Computer Science University of Western Ontario London, Ontario, Canada,
Creating an Agent of Doom: A Visual Reinforcement Learning Approach
Creating an Agent of Doom: A Visual Reinforcement Learning Approach Michael Lowney Department of Electrical Engineering Stanford University mlowney@stanford.edu Robert Mahieu Department of Electrical Engineering
Sketch-a-Net: a Deep Neural Network that Beats Humans
Sketch-a-Net: a Deep Neural Network that Beats Humans Yu, Q; Yang, Y; Liu, F; SONG, Y; Xiang, T; Hospedales, T DOI: 0.00/s-0-0- For additional information about this publication click this link. http://qmro.qmul.ac.uk/xmlui/handle//
The Art of Neural Nets
The Art of Neural Nets Marco Tavora marcotav65@gmail.com Preamble The challenge of recognizing artists given their paintings has been, for a long time, far beyond the capability of algorithms. Recent advances
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. ECE 289G: Paper Presentation #3 Philipp Gysel
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition ECE 289G: Paper Presentation #3 Philipp Gysel Autonomous Car ECE 289G Paper Presentation, Philipp Gysel Slide 2 Source: maps.google.com
arxiv: v2 [cs.sd] 22 May 2017
![arxiv: v2 [cs.sd] 22 May 2017](/thumbs/72/66381162.jpg "arxiv: v2 [cs.sd] 22 May 2017")
SAMPLE-LEVEL DEEP CONVOLUTIONAL NEURAL NETWORKS FOR MUSIC AUTO-TAGGING USING RAW WAVEFORMS Jongpil Lee Jiyoung Park Keunhyoung Luke Kim Juhan Nam Korea Advanced Institute of Science and Technology (KAIST)
Author(s) Corr, Philip J.; Silvestre, Guenole C.; Bleakley, Christopher J. The Irish Pattern Recognition & Classification Society
Provided by the author(s) and University College Dublin Library in accordance with publisher policies. Please cite the published version when available. Title Open Source Dataset and Deep Learning Models
Neuro-inspired A.I. Z A F E I R I O S F O U N TA S D E PA R T M E N T O F C O M P U T I N G I M P E R I A L C O L L E G E LO N D O N
Neuro-inspired A.I. LECTURE 3 Z A F E I R I O S F O U N TA S D E PA R T M E N T O F C O M P U T I N G I M P E R I A L C O L L E G E LO N D O N Overview First hour Motivation and history Spiking neural
DSNet: An Efficient CNN for Road Scene Segmentation
DSNet: An Efficient CNN for Road Scene Segmentation Ping-Rong Chen 1 Hsueh-Ming Hang 1 1 National Chiao Tung University {james50120.ee05g, hmhang}@nctu.edu.tw Sheng-Wei Chan 2 Jing-Jhih Lin 2 2 Industrial
Deep Neural Network Architectures for Modulation Classification
Deep Neural Network Architectures for Modulation Classification Xiaoyu Liu, Diyu Yang, and Aly El Gamal School of Electrical and Computer Engineering Purdue University Email: {liu1962, yang1467, elgamala}@purdue.edu
arxiv: v3 [cs.cv] 18 Dec 2018
![arxiv: v3 [cs.cv] 18 Dec 2018](/thumbs/96/128789272.jpg "arxiv: v3 [cs.cv] 18 Dec 2018")
Video Colorization using CNNs and Keyframes extraction: An application in saving bandwidth Ankur Singh 1 Anurag Chanani 2 Harish Karnick 3 arxiv:1812.03858v3 [cs.cv] 18 Dec 2018 Abstract In this paper,
Convolutional Networks for Image Segmentation: U-Net 1, DeconvNet 2, and SegNet 3
Convolutional Networks for Image Segmentation: U-Net 1, DeconvNet 2, and SegNet 3 1 Olaf Ronneberger, Philipp Fischer, Thomas Brox (Freiburg, Germany) 2 Hyeonwoo Noh, Seunghoon Hong, Bohyung Han (POSTECH,
Fusion of Stereo Vision for Pedestrian Recognition using Convolutional Neural Networks
Fusion of Stereo Vision for Pedestrian Recognition using Convolutional Neural Networks Danut Ovidiu Pop, Alexandrina Rogozan, Fawzi Nashashibi, Abdelaziz Bensrhair To cite this version: Danut Ovidiu Pop,
Radio Deep Learning Efforts Showcase Presentation
Radio Deep Learning Efforts Showcase Presentation November 2016 hume@vt.edu www.hume.vt.edu Tim O Shea Senior Research Associate Program Overview Program Objective: Rethink fundamental approaches to how
11/13/18. Introduction to RNNs for NLP. About Me. Overview SHANG GAO
Introduction to RNNs for NLP SHANG GAO About Me PhD student in the Data Science and Engineering program Took Deep Learning last year Work in the Biomedical Sciences, Engineering, and Computing group at
Adversarial Robustness for Aligned AI
Adversarial Robustness for Aligned AI Ian Goodfellow, Staff Research NIPS 2017 Workshop on Aligned Artificial Intelligence Many thanks to Catherine Olsson for feedback on drafts The Alignment Problem (This
Generating an appropriate sound for a video using WaveNet.
Australian National University College of Engineering and Computer Science Master of Computing Generating an appropriate sound for a video using WaveNet. COMP 8715 Individual Computing Project Taku Ueki