Is Bigger CNN Better? Samer Hijazi on behalf of IPG CTO Group Embedded Neural Networks Summit (enns2016) San Jose Feb. 9th

Size: px
Start display at page:

Download "Is Bigger CNN Better? Samer Hijazi on behalf of IPG CTO Group Embedded Neural Networks Summit (enns2016) San Jose Feb. 9th"

Transcription

1 Is Bigger CNN Better? Samer Hijazi on behalf of IPG CTO Group Embedded Neural Networks Summit (enns2016) San Jose Feb. 9th

2 Today s Story Why does CNN matter to the embedded world? How to enable CNN in embedded devices? Complexity vs. performance tradeoff? Concluding thoughts Cadence Design Systems, Inc. All rights reserved.

3 Why does CNN matter to the embedded world?

4 What is the semiconductor industry asking for? We are trying to motivate bridging the gap between academic developments and the semiconductor industry needs Cadence Design Systems, Inc. All rights reserved.

5 CNN is growing fast Today s deep learning industry motto is Bigger is Better Net name Layers Parameters MAC LeNet-5 for MNIST (1998) 7 58,996 77,484 M ImageNet (2012) 8 60 M 1.1 G Deepface (2014) 8 >120 M 1.4 G Ensemble CNN(2014) 16x20 23 M 1.4 G FaceNet (2014) M 1.6 G VGG for face (2015) M 15.5 G Embedded devices power, price, and form-factor requirements can not accommodate this trend Dr. Stephen Hicks, Nuffield Department of Clinical Neurosciences, University of Oxford Cadence Design Systems, Inc. All rights reserved.

6 Complexity vs Performance Performance Cloud Budget Target recognition rate Current Industry Trend Complexity Cadence Design Systems, Inc. All rights reserved. Embedded Device Budget

7 Methodology Step 1. Train a network to your heart s desire Use the tool/programming language you are most familiar with (e.g., caffe, tensor flow, matcovnet, theano, CNTK, torch, ) Step 2. Iteratively reduce the key parameters Utilize: Statistics Linear algebra Use the validation set as guidance for convergence Cadence Design Systems, Inc. All rights reserved.

8 Balancing performance and complexity

9 How to do it? Reducing number of feature maps AlexNet has up to 384 feature maps. Reducing network depth Oxford VGG face recognition network has 37 layers. Divide and Conquer Do we need them all? Are they all equally important? How many classes should a single network handle? What can a single device see? Cadence Design Systems, Inc. All rights reserved.

10 Feature Map Reduction

11 Feature Maps Number of Feature Maps = Number of 3-D filters These filters are highly correlated. Input feature maps/images Output feature maps Feature Map Feature Map Convolutional Layer Cadence Design Systems, Inc. All rights reserved.

12 Redundancies in Filter Weights Q: How many filters do we need? A: How many independent filters can we really have? Back to linear algebra Cadence Design Systems, Inc. All rights reserved.

13 Linear Algebra 101 The space spanned by a vector of size N is referred to as N - dimensional space v3 c 3 a i Any vector in this space can be expressed as a linear combination of the basis of the space v2 c 2 c 1 v1 It can be shown that there is only N independent basis in the space a i = j=1 N c j v j Cadence Design Systems, Inc. All rights reserved.

14 Linear Algebra 101 (cont d) Q: How to find v j s? A: SVD (Singular Value Decomposition) M N M M N N N M 0 A U Σ V T A = UΣ V T Cadence Design Systems, Inc. All rights reserved.

15 Eigen-basis Size Reduction for the Convolutional Filters The i-th convolutional layer C i is of size L i W i H i K i L i, W i, H i : 3D filter size K i : number of feature maps Form the filter coefficients into an matrix A of size M K i Apply SVD decomposition: A = UΣ V T Use the M dominating basis (associated with the M largest singular vales) to initialize the filter at C i Size Reduction Cadence Design Systems, Inc. All rights reserved.

16 Results Analysis Traffic Sign Recognition German Traffic Sign Recognition Benchmark (GTSRB) images of German road signs in 43 classes Size of Images varies between 15x15 to 222x193 Images grouped by Class and Track with atleast 30 images per track. Images available as Color Images (RGB), HOG features, Haar features and Color Histograms Cadence Design Systems, Inc. All rights reserved.

17 Results Analysis Traffic Sign Recognition (Cont d) Performance(% Correct Detection) 99.9% 99.7% 99.5% 99.3% 99.1% 98.9% GTSRB Best result achieved by HCNN Baseline (LeNet) Best prev. result Eliminating the redundancy in the coefficients Improve training efficiency and performance simultaneously control performance degradation as a function of complexity reduction 98.7% 1,000,000 10,000, ,000,000 1,000,000,000 Complexity (MACs per Frame) Log-scale Cadence Design Systems, Inc. All rights reserved.

18 Results Analysis Handwriting Recognition The database is provided by Mixed National Institute of Standards and Technology (MNIST) 60,000 training images and 10,000 testing images Black and white images Size normalized to fit in a 20 by 20 pixel box Centered in a 28 by 28 field Cadence Design Systems, Inc. All rights reserved.

19 Results Analysis Handwriting Recognition (Cont d) Performance (% Correction Detection) 99.20% 99.15% 99.10% 99.05% 99.00% 98.95% MNIST 98.90% Complexity (MACs per frame) Log-scale Baseline (LeNet-5) Eliminating the redundancy in the coefficients Improve training efficiency and performance simultaneously control performance degradation as a function of complexity reduction Cadence Design Systems, Inc. All rights reserved.

20 Network Depth Reduction

21 Network Depth Q1: Are all layers equally important? Q2: How to utilize the difference among layers importance to reduce complexity? Cadence Design Systems, Inc. All rights reserved.

22 Are all layers equally important? Define a metric to measure the amount of refinement each layer can contribute. C1 C2 C3 C4 C5 input C6 pool relu relu pool relu pool relu relu dropout Level Quality Metric C5 C1 C2 C3 C Cadence Design Systems, Inc. All rights reserved.

23 How to use the layer quality (LQ) metric? Eliminate low LQ layers and distribute their functionality over the entire network. C1 C2 C3 C4 C5 input C6 pool relu relu pool relu pool relu relu dropout Cadence Design Systems, Inc. All rights reserved.

24 How to use the layer quality (LQ) metric? Eliminate low LQ layers and distribute their functionality over the entire network. This can be tricky due to the nonlinear components of the network. C1 C2 C4 C5 input C6 pool relu pool relu pool relu relu dropout An alternative way to use LQ metric is to allocate the computational resources based on LQ Cadence Design Systems, Inc. All rights reserved.

25 Divide and Conquer Presenter Name and Title (Arial 16pt) Event Name Location Date

26 What is this? An animal? Wolf? Cadence Design Systems, Inc. All rights reserved.

27 What is this? An animal? Wolf? Cute Wolf? Cadence Design Systems, Inc. All rights reserved.

28 What is this? Barking Husky Howling Wolf Cadence Design Systems, Inc. All rights reserved.

29 Hierarchical Recognition Concept Not all images are equally hard to recognize Dynamically allocate resources based on the problem difficulty. Let CNN automate the partitioning process Cadence Design Systems, Inc. All rights reserved.

30 GTSRB Ideal Traffic Sign Speed Limit Signs Other Prohibitory Signs Derestriction Signs Mandatory Signs Other Prohibitory Signs Cadence Design Systems, Inc. All rights reserved.

31 Hierarchical-CNN for TSR MC-CNN 1 FC-CNN MC-CNN 2 Level-1: Family Classifier CNN (FC-CNN) Level-2: Member Classifier CNN (MC-CNN)... MC-CNN 5 Using hierarchical CNN we are able to dynamically allocate resources in accordance with the problem difficulty The CNN-oriented family clustering method groups signs into subsets that is more preferable than the pre-defined subset for a CNN classifier. Family 1 Decision Decision Decision Family different CNNs for classification, each has lower complexity than one-vs-all classifier Family 3 Family 4 Family Cadence Design Systems, Inc. All rights reserved.

32 Results CCR% Team Method Cadence HCNN + color Tsinghua Hinge Loss Trained CNN IDSIA Committee of CNNs Cadence Modified UYN INI-RTCV Human (best individual) Sermanet (UNY) Updated multi-scale CNN INI-RTCV Human (average) Sermanet (UNY) Multi-scale CNN CAOR) Random Forest INI-RTCV LDA (HOG 2) Cadence Design Systems, Inc. All rights reserved.

33 Alternative Network Architecture Hierarchical decision process can be incorporated in the network training if we allow gradual decision after each layer Input Conv Pooling ReLU Conv Pooling ReLU Fully Connected Cadence Design Systems, Inc. All rights reserved.

34 Closing Thoughts

35 What is the semiconductor industry asking for? We are trying to motivate bridging the gap between academic developments and the semiconductor industry needs Cadence Design Systems, Inc. All rights reserved.

36 See you in Vegas! The premier summer conference for the computer vision community Computer Vision Pattern Recognition (CVPR2016) will be held in Vegas from June Cadence will be offering a tutorial on low complexity recognition SoCs. Embedded CNN Local vs Cloud Compute, why and why not? Complexity Reduction Techniques Cadence Design Systems, Inc. All rights reserved.

37

Index. Springer Nature Switzerland AG 2019 B. Moons et al., Embedded Deep Learning,

Index. Springer Nature Switzerland AG 2019 B. Moons et al., Embedded Deep Learning, Index A Algorithmic noise tolerance (ANT), 93 94 Application specific instruction set processors (ASIPs), 115 116 Approximate computing application level, 95 circuits-levels, 93 94 DAS and DVAS, 107 110

More information

Convolutional Neural Networks

Convolutional Neural Networks NPFL114, Lecture 4 Convolutional Neural Networks Milan Straka March 25, 2019 Charles University in Prague Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics unless otherwise

More information

Object Detection. Part1. Presenter: Dae-Yong

Object Detection. Part1. Presenter: Dae-Yong Object Part1 Presenter: Dae-Yong Contents 1. What is an Object? 2. Traditional Object Detector 3. Deep Learning-based Object Detector What is an Object? Subset of Object Recognition What is an Object?

More information

Deep Learning & Neural Networks

Deep Learning & Neural Networks Deep Learning & Neural Networks Machine Learning CSE4546 Sham Kakade University of Washington November 29, 2016 Sham Kakade 1 Announcements: HW4 posted Poster Session Thurs, Dec 8 Today: Review: EM Neural

More information

Dynamic Routing Between Capsules

Dynamic Routing Between Capsules Report Explainable Machine Learning Dynamic Routing Between Capsules Author: Michael Dorkenwald Supervisor: Dr. Ullrich Köthe 28. Juni 2018 Inhaltsverzeichnis 1 Introduction 2 2 Motivation 2 3 CapusleNet

More information

Face Recognition A Deep Learning Approach

Face Recognition A Deep Learning Approach Face Recognition A Deep Learning Approach Lihi Shiloh Tal Perl Deep Learning Seminar 2 Outline What about Cat recognition? Classical face recognition Modern face recognition DeepFace FaceNet Comparison

More information

DEEP LEARNING WITH GPUS Maxim Milakov, Senior HPC DevTech Engineer, NVIDIA

DEEP LEARNING WITH GPUS Maxim Milakov, Senior HPC DevTech Engineer, NVIDIA DEEP LEARNING WITH GPUS Maxim Milakov, Senior HPC DevTech Engineer, NVIDIA TOPICS COVERED Convolutional Networks Deep Learning Use Cases GPUs cudnn 2 MACHINE LEARNING! Training! Train the model from supervised

More information

Inception and Residual Networks. Hantao Zhang. Deep Learning with Python.

Inception and Residual Networks. Hantao Zhang. Deep Learning with Python. Inception and Residual Networks Hantao Zhang Deep Learning with Python https://en.wikipedia.org/wiki/residual_neural_network Deep Neural Network Progress from Large Scale Visual Recognition Challenge (ILSVRC)

More information

Machine Learning. Deep Learning. Eric Xing (and Pengtao Xie) , Fall Lecture 8, October 6, Eric CMU,

Machine Learning. Deep Learning. Eric Xing (and Pengtao Xie) , Fall Lecture 8, October 6, Eric CMU, Machine Learning 10-701, Fall 2015 Deep Learning Eric Xing (and Pengtao Xie) Lecture 8, October 6, 2015 Eric Xing @ CMU, 2015 1 A perennial challenge in computer vision: feature engineering SIFT Spin image

More information

Convolutional Neural Networks. Computer Vision Jia-Bin Huang, Virginia Tech

Convolutional Neural Networks. Computer Vision Jia-Bin Huang, Virginia Tech Convolutional Neural Networks Computer Vision Jia-Bin Huang, Virginia Tech Today s class Overview Convolutional Neural Network (CNN) Training CNN Understanding and Visualizing CNN Image Categorization:

More information

Throughput-Optimized OpenCL-based FPGA Accelerator for Large-Scale Convolutional Neural Networks

Throughput-Optimized OpenCL-based FPGA Accelerator for Large-Scale Convolutional Neural Networks Throughput-Optimized OpenCL-based FPGA Accelerator for Large-Scale Convolutional Neural Networks Naveen Suda, Vikas Chandra *, Ganesh Dasika *, Abinash Mohanty, Yufei Ma, Sarma Vrudhula, Jae-sun Seo, Yu

More information

Deep Learning for Computer Vision II

Deep Learning for Computer Vision II IIIT Hyderabad Deep Learning for Computer Vision II C. V. Jawahar Paradigm Shift Feature Extraction (SIFT, HoG, ) Part Models / Encoding Classifier Sparrow Feature Learning Classifier Sparrow L 1 L 2 L

More information

Fuzzy Set Theory in Computer Vision: Example 3

Fuzzy Set Theory in Computer Vision: Example 3 Fuzzy Set Theory in Computer Vision: Example 3 Derek T. Anderson and James M. Keller FUZZ-IEEE, July 2017 Overview Purpose of these slides are to make you aware of a few of the different CNN architectures

More information

Machine Learning. The Breadth of ML Neural Networks & Deep Learning. Marc Toussaint. Duy Nguyen-Tuong. University of Stuttgart

Machine Learning. The Breadth of ML Neural Networks & Deep Learning. Marc Toussaint. Duy Nguyen-Tuong. University of Stuttgart Machine Learning The Breadth of ML Neural Networks & Deep Learning Marc Toussaint University of Stuttgart Duy Nguyen-Tuong Bosch Center for Artificial Intelligence Summer 2017 Neural Networks Consider

More information

Tutorial on Keras CAP ADVANCED COMPUTER VISION SPRING 2018 KISHAN S ATHREY

Tutorial on Keras CAP ADVANCED COMPUTER VISION SPRING 2018 KISHAN S ATHREY Tutorial on Keras CAP 6412 - ADVANCED COMPUTER VISION SPRING 2018 KISHAN S ATHREY Deep learning packages TensorFlow Google PyTorch Facebook AI research Keras Francois Chollet (now at Google) Chainer Company

More information

Spatial Localization and Detection. Lecture 8-1

Spatial Localization and Detection. Lecture 8-1 Lecture 8: Spatial Localization and Detection Lecture 8-1 Administrative - Project Proposals were due on Saturday Homework 2 due Friday 2/5 Homework 1 grades out this week Midterm will be in-class on Wednesday

More information

CNN Basics. Chongruo Wu

CNN Basics. Chongruo Wu CNN Basics Chongruo Wu Overview 1. 2. 3. Forward: compute the output of each layer Back propagation: compute gradient Updating: update the parameters with computed gradient Agenda 1. Forward Conv, Fully

More information

Intro to Deep Learning. Slides Credit: Andrej Karapathy, Derek Hoiem, Marc Aurelio, Yann LeCunn

Intro to Deep Learning. Slides Credit: Andrej Karapathy, Derek Hoiem, Marc Aurelio, Yann LeCunn Intro to Deep Learning Slides Credit: Andrej Karapathy, Derek Hoiem, Marc Aurelio, Yann LeCunn Why this class? Deep Features Have been able to harness the big data in the most efficient and effective

More information

Binary Convolutional Neural Network on RRAM

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

More information

CS 2750: Machine Learning. Neural Networks. Prof. Adriana Kovashka University of Pittsburgh April 13, 2016

CS 2750: Machine Learning. Neural Networks. Prof. Adriana Kovashka University of Pittsburgh April 13, 2016 CS 2750: Machine Learning Neural Networks Prof. Adriana Kovashka University of Pittsburgh April 13, 2016 Plan for today Neural network definition and examples Training neural networks (backprop) Convolutional

More information

Deep Learning with Tensorflow AlexNet

Deep Learning with Tensorflow   AlexNet Machine Learning and Computer Vision Group Deep Learning with Tensorflow http://cvml.ist.ac.at/courses/dlwt_w17/ AlexNet Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton, "Imagenet classification

More information

Inception Network Overview. David White CS793

Inception Network Overview. David White CS793 Inception Network Overview David White CS793 So, Leonardo DiCaprio dreams about dreaming... https://m.media-amazon.com/images/m/mv5bmjaxmzy3njcxnf5bml5banbnxkftztcwnti5otm0mw@@._v1_sy1000_cr0,0,675,1 000_AL_.jpg

More information

Deep Learning for Computer Vision with MATLAB By Jon Cherrie

Deep Learning for Computer Vision with MATLAB By Jon Cherrie Deep Learning for Computer Vision with MATLAB By Jon Cherrie 2015 The MathWorks, Inc. 1 Deep learning is getting a lot of attention "Dahl and his colleagues won $22,000 with a deeplearning system. 'We

More information

DECISION TREES & RANDOM FORESTS X CONVOLUTIONAL NEURAL NETWORKS

DECISION TREES & RANDOM FORESTS X CONVOLUTIONAL NEURAL NETWORKS DECISION TREES & RANDOM FORESTS X CONVOLUTIONAL NEURAL NETWORKS Deep Neural Decision Forests Microsoft Research Cambridge UK, ICCV 2015 Decision Forests, Convolutional Networks and the Models in-between

More information

A performance comparison of Deep Learning frameworks on KNL

A performance comparison of Deep Learning frameworks on KNL A performance comparison of Deep Learning frameworks on KNL R. Zanella, G. Fiameni, M. Rorro Middleware, Data Management - SCAI - CINECA IXPUG Bologna, March 5, 2018 Table of Contents 1. Problem description

More information

Safety verification for deep neural networks

Safety verification for deep neural networks Safety verification for deep neural networks Marta Kwiatkowska Department of Computer Science, University of Oxford UC Berkeley, 8 th November 2016 Setting the scene Deep neural networks have achieved

More information

High Performance Computing

High Performance Computing High Performance Computing 9th Lecture 2016/10/28 YUKI ITO 1 Selected Paper: vdnn: Virtualized Deep Neural Networks for Scalable, MemoryEfficient Neural Network Design Minsoo Rhu, Natalia Gimelshein, Jason

More information

CNNS FROM THE BASICS TO RECENT ADVANCES. Dmytro Mishkin Center for Machine Perception Czech Technical University in Prague

CNNS FROM THE BASICS TO RECENT ADVANCES. Dmytro Mishkin Center for Machine Perception Czech Technical University in Prague CNNS FROM THE BASICS TO RECENT ADVANCES Dmytro Mishkin Center for Machine Perception Czech Technical University in Prague ducha.aiki@gmail.com OUTLINE Short review of the CNN design Architecture progress

More information

Computer Vision Lecture 16

Computer Vision Lecture 16 Computer Vision Lecture 16 Deep Learning for Object Categorization 14.01.2016 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Announcements Seminar registration period

More information

Revolutionizing the Datacenter

Revolutionizing the Datacenter Power-Efficient Machine Learning using FPGAs on POWER Systems Ralph Wittig, Distinguished Engineer Office of the CTO, Xilinx Revolutionizing the Datacenter Join the Conversation #OpenPOWERSummit Top-5

More information

Study of Residual Networks for Image Recognition

Study of Residual Networks for Image Recognition Study of Residual Networks for Image Recognition Mohammad Sadegh Ebrahimi Stanford University sadegh@stanford.edu Hossein Karkeh Abadi Stanford University hosseink@stanford.edu Abstract Deep neural networks

More information

Deep Learning Based Real-time Object Recognition System with Image Web Crawler

Deep Learning Based Real-time Object Recognition System with Image Web Crawler , pp.103-110 http://dx.doi.org/10.14257/astl.2016.142.19 Deep Learning Based Real-time Object Recognition System with Image Web Crawler Myung-jae Lee 1, Hyeok-june Jeong 1, Young-guk Ha 2 1 Department

More information

Deep Neural Networks:

Deep Neural Networks: Deep Neural Networks: Part II Convolutional Neural Network (CNN) Yuan-Kai Wang, 2016 Web site of this course: http://pattern-recognition.weebly.com source: CNN for ImageClassification, by S. Lazebnik,

More information

Deep Learning in Visual Recognition. Thanks Da Zhang for the slides

Deep Learning in Visual Recognition. Thanks Da Zhang for the slides Deep Learning in Visual Recognition Thanks Da Zhang for the slides Deep Learning is Everywhere 2 Roadmap Introduction Convolutional Neural Network Application Image Classification Object Detection Object

More information

DL Tutorial. Xudong Cao

DL Tutorial. Xudong Cao DL Tutorial Xudong Cao Historical Line 1960s Perceptron 1980s MLP BP algorithm 2006 RBM unsupervised learning 2012 AlexNet ImageNet Comp. 2014 GoogleNet VGGNet ImageNet Comp. Rule based AI algorithm Game

More information

COMP 551 Applied Machine Learning Lecture 16: Deep Learning

COMP 551 Applied Machine Learning Lecture 16: Deep Learning COMP 551 Applied Machine Learning Lecture 16: Deep Learning Instructor: Ryan Lowe (ryan.lowe@cs.mcgill.ca) Slides mostly by: Class web page: www.cs.mcgill.ca/~hvanho2/comp551 Unless otherwise noted, all

More information

CS 523: Multimedia Systems

CS 523: Multimedia Systems CS 523: Multimedia Systems Angus Forbes creativecoding.evl.uic.edu/courses/cs523 Today - Convolutional Neural Networks - Work on Project 1 http://playground.tensorflow.org/ Convolutional Neural Networks

More information

Using Machine Learning for Classification of Cancer Cells

Using Machine Learning for Classification of Cancer Cells Using Machine Learning for Classification of Cancer Cells Camille Biscarrat University of California, Berkeley I Introduction Cell screening is a commonly used technique in the development of new drugs.

More information

FaceNet. Florian Schroff, Dmitry Kalenichenko, James Philbin Google Inc. Presentation by Ignacio Aranguren and Rahul Rana

FaceNet. Florian Schroff, Dmitry Kalenichenko, James Philbin Google Inc. Presentation by Ignacio Aranguren and Rahul Rana FaceNet Florian Schroff, Dmitry Kalenichenko, James Philbin Google Inc. Presentation by Ignacio Aranguren and Rahul Rana Introduction FaceNet learns a mapping from face images to a compact Euclidean Space

More information

Low-Power Neural Processor for Embedded Human and Face detection

Low-Power Neural Processor for Embedded Human and Face detection Low-Power Neural Processor for Embedded Human and Face detection Olivier Brousse 1, Olivier Boisard 1, Michel Paindavoine 1,2, Jean-Marc Philippe, Alexandre Carbon (1) GlobalSensing Technologies (GST)

More information

Deep Residual Learning

Deep Residual Learning Deep Residual Learning MSRA @ ILSVRC & COCO 2015 competitions Kaiming He with Xiangyu Zhang, Shaoqing Ren, Jifeng Dai, & Jian Sun Microsoft Research Asia (MSRA) MSRA @ ILSVRC & COCO 2015 Competitions 1st

More information

Fuzzy Set Theory in Computer Vision: Example 3, Part II

Fuzzy Set Theory in Computer Vision: Example 3, Part II Fuzzy Set Theory in Computer Vision: Example 3, Part II Derek T. Anderson and James M. Keller FUZZ-IEEE, July 2017 Overview Resource; CS231n: Convolutional Neural Networks for Visual Recognition https://github.com/tuanavu/stanford-

More information

MoonRiver: Deep Neural Network in C++

MoonRiver: Deep Neural Network in C++ MoonRiver: Deep Neural Network in C++ Chung-Yi Weng Computer Science & Engineering University of Washington chungyi@cs.washington.edu Abstract Artificial intelligence resurges with its dramatic improvement

More information

All You Want To Know About CNNs. Yukun Zhu

All You Want To Know About CNNs. Yukun Zhu All You Want To Know About CNNs Yukun Zhu Deep Learning Deep Learning Image from http://imgur.com/ Deep Learning Image from http://imgur.com/ Deep Learning Image from http://imgur.com/ Deep Learning Image

More information

Using Capsule Networks. for Image and Speech Recognition Problems. Yan Xiong

Using Capsule Networks. for Image and Speech Recognition Problems. Yan Xiong Using Capsule Networks for Image and Speech Recognition Problems by Yan Xiong A Thesis Presented in Partial Fulfillment of the Requirements for the Degree Master of Science Approved November 2018 by the

More information

POINT CLOUD DEEP LEARNING

POINT CLOUD DEEP LEARNING POINT CLOUD DEEP LEARNING Innfarn Yoo, 3/29/28 / 57 Introduction AGENDA Previous Work Method Result Conclusion 2 / 57 INTRODUCTION 3 / 57 2D OBJECT CLASSIFICATION Deep Learning for 2D Object Classification

More information

COMP9444 Neural Networks and Deep Learning 7. Image Processing. COMP9444 c Alan Blair, 2017

COMP9444 Neural Networks and Deep Learning 7. Image Processing. COMP9444 c Alan Blair, 2017 COMP9444 Neural Networks and Deep Learning 7. Image Processing COMP9444 17s2 Image Processing 1 Outline Image Datasets and Tasks Convolution in Detail AlexNet Weight Initialization Batch Normalization

More information

Generative Modeling with Convolutional Neural Networks. Denis Dus Data Scientist at InData Labs

Generative Modeling with Convolutional Neural Networks. Denis Dus Data Scientist at InData Labs Generative Modeling with Convolutional Neural Networks Denis Dus Data Scientist at InData Labs What we will discuss 1. 2. 3. 4. Discriminative vs Generative modeling Convolutional Neural Networks How to

More information

C-Brain: A Deep Learning Accelerator

C-Brain: A Deep Learning Accelerator C-Brain: A Deep Learning Accelerator that Tames the Diversity of CNNs through Adaptive Data-level Parallelization Lili Song, Ying Wang, Yinhe Han, Xin Zhao, Bosheng Liu, Xiaowei Li State Key Laboratory

More information

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space Sikai Zhong February 14, 2018 COMPUTER SCIENCE Table of contents 1. PointNet 2. PointNet++ 3. Experiments 1 PointNet Property

More information

Convolutional Neural Networks

Convolutional Neural Networks Lecturer: Barnabas Poczos Introduction to Machine Learning (Lecture Notes) Convolutional Neural Networks Disclaimer: These notes have not been subjected to the usual scrutiny reserved for formal publications.

More information

Scalable and Modularized RTL Compilation of Convolutional Neural Networks onto FPGA

Scalable and Modularized RTL Compilation of Convolutional Neural Networks onto FPGA Scalable and Modularized RTL Compilation of Convolutional Neural Networks onto FPGA Yufei Ma, Naveen Suda, Yu Cao, Jae-sun Seo, Sarma Vrudhula School of Electrical, Computer and Energy Engineering School

More information

6. Convolutional Neural Networks

6. Convolutional Neural Networks 6. Convolutional Neural Networks CS 519 Deep Learning, Winter 2017 Fuxin Li With materials from Zsolt Kira Quiz coming up Next Thursday (2/2) 20 minutes Topics: Optimization Basic neural networks No Convolutional

More information

ConvolutionalNN's... ConvNet's... deep learnig

ConvolutionalNN's... ConvNet's... deep learnig Deep Learning ConvolutionalNN's... ConvNet's... deep learnig Markus Thaler, TG208 tham@zhaw.ch www.zhaw.ch/~tham Martin Weisenhorn, TB427 weie@zhaw.ch 20.08.2018 1 Neural Networks Classification: up to

More information

Deep Learning Explained Module 4: Convolution Neural Networks (CNN or Conv Nets)

Deep Learning Explained Module 4: Convolution Neural Networks (CNN or Conv Nets) Deep Learning Explained Module 4: Convolution Neural Networks (CNN or Conv Nets) Sayan D. Pathak, Ph.D., Principal ML Scientist, Microsoft Roland Fernandez, Senior Researcher, Microsoft Module Outline

More information

Deep Convolutional Neural Network using Triplet of Faces, Deep Ensemble, and Scorelevel Fusion for Face Recognition

Deep Convolutional Neural Network using Triplet of Faces, Deep Ensemble, and Scorelevel Fusion for Face Recognition IEEE 2017 Conference on Computer Vision and Pattern Recognition Deep Convolutional Neural Network using Triplet of Faces, Deep Ensemble, and Scorelevel Fusion for Face Recognition Bong-Nam Kang*, Yonghyun

More information

Ryerson University CP8208. Soft Computing and Machine Intelligence. Naive Road-Detection using CNNS. Authors: Sarah Asiri - Domenic Curro

Ryerson University CP8208. Soft Computing and Machine Intelligence. Naive Road-Detection using CNNS. Authors: Sarah Asiri - Domenic Curro Ryerson University CP8208 Soft Computing and Machine Intelligence Naive Road-Detection using CNNS Authors: Sarah Asiri - Domenic Curro April 24 2016 Contents 1 Abstract 2 2 Introduction 2 3 Motivation

More information

Defense Data Generation in Distributed Deep Learning System Se-Yoon Oh / ADD-IDAR

Defense Data Generation in Distributed Deep Learning System Se-Yoon Oh / ADD-IDAR Defense Data Generation in Distributed Deep Learning System Se-Yoon Oh / 2017. 10. 31 syoh@add.re.kr Page 1/36 Overview 1. Introduction 2. Data Generation Synthesis 3. Distributed Deep Learning 4. Conclusions

More information

Object Detection Based on Deep Learning

Object Detection Based on Deep Learning Object Detection Based on Deep Learning Yurii Pashchenko AI Ukraine 2016, Kharkiv, 2016 Image classification (mostly what you ve seen) http://tutorial.caffe.berkeleyvision.org/caffe-cvpr15-detection.pdf

More information

Deep Learning and Its Applications

Deep Learning and Its Applications Convolutional Neural Network and Its Application in Image Recognition Oct 28, 2016 Outline 1 A Motivating Example 2 The Convolutional Neural Network (CNN) Model 3 Training the CNN Model 4 Issues and Recent

More information

Implementation of Deep Convolutional Neural Net on a Digital Signal Processor

Implementation of Deep Convolutional Neural Net on a Digital Signal Processor Implementation of Deep Convolutional Neural Net on a Digital Signal Processor Elaina Chai December 12, 2014 1. Abstract In this paper I will discuss the feasibility of an implementation of an algorithm

More information

Keras: Handwritten Digit Recognition using MNIST Dataset

Keras: Handwritten Digit Recognition using MNIST Dataset Keras: Handwritten Digit Recognition using MNIST Dataset IIT PATNA January 31, 2018 1 / 30 OUTLINE 1 Keras: Introduction 2 Installing Keras 3 Keras: Building, Testing, Improving A Simple Network 2 / 30

More information

CSE 559A: Computer Vision

CSE 559A: Computer Vision CSE 559A: Computer Vision Fall 2018: T-R: 11:30-1pm @ Lopata 101 Instructor: Ayan Chakrabarti (ayan@wustl.edu). Course Staff: Zhihao Xia, Charlie Wu, Han Liu http://www.cse.wustl.edu/~ayan/courses/cse559a/

More information

Deconvolution Networks

Deconvolution Networks Deconvolution Networks Johan Brynolfsson Mathematical Statistics Centre for Mathematical Sciences Lund University December 6th 2016 1 / 27 Deconvolution Neural Networks 2 / 27 Image Deconvolution True

More information

R-FCN: Object Detection with Really - Friggin Convolutional Networks

R-FCN: Object Detection with Really - Friggin Convolutional Networks R-FCN: Object Detection with Really - Friggin Convolutional Networks Jifeng Dai Microsoft Research Li Yi Tsinghua Univ. Kaiming He FAIR Jian Sun Microsoft Research NIPS, 2016 Or Region-based Fully Convolutional

More information

Como funciona o Deep Learning

Como funciona o Deep Learning Como funciona o Deep Learning Moacir Ponti (com ajuda de Gabriel Paranhos da Costa) ICMC, Universidade de São Paulo Contact: www.icmc.usp.br/~moacir moacir@icmc.usp.br Uberlandia-MG/Brazil October, 2017

More information

Convolutional Neural Networks for Facial Expression Recognition

Convolutional Neural Networks for Facial Expression Recognition Convolutional Neural Networks for Facial Expression Recognition Shima Alizadeh Stanford University shima86@stanford.edu Azar Fazel Stanford University azarf@stanford.edu Abstract In this project, we have

More information

Brainchip OCTOBER

Brainchip OCTOBER Brainchip OCTOBER 2017 1 Agenda Neuromorphic computing background Akida Neuromorphic System-on-Chip (NSoC) Brainchip OCTOBER 2017 2 Neuromorphic Computing Background Brainchip OCTOBER 2017 3 A Brief History

More information

Content-Based Image Recovery

Content-Based Image Recovery Content-Based Image Recovery Hong-Yu Zhou and Jianxin Wu National Key Laboratory for Novel Software Technology Nanjing University, China zhouhy@lamda.nju.edu.cn wujx2001@nju.edu.cn Abstract. We propose

More information

Computer Vision Lecture 16

Computer Vision Lecture 16 Announcements Computer Vision Lecture 16 Deep Learning Applications 11.01.2017 Seminar registration period starts on Friday We will offer a lab course in the summer semester Deep Robot Learning Topic:

More information

Classification of objects from Video Data (Group 30)

Classification of objects from Video Data (Group 30) Classification of objects from Video Data (Group 30) Sheallika Singh 12665 Vibhuti Mahajan 12792 Aahitagni Mukherjee 12001 M Arvind 12385 1 Motivation Video surveillance has been employed for a long time

More information

Joint Object Detection and Viewpoint Estimation using CNN features

Joint Object Detection and Viewpoint Estimation using CNN features Joint Object Detection and Viewpoint Estimation using CNN features Carlos Guindel, David Martín and José M. Armingol cguindel@ing.uc3m.es Intelligent Systems Laboratory Universidad Carlos III de Madrid

More information

Scaling Convolutional Neural Networks on Reconfigurable Logic Michaela Blott, Principal Engineer, Xilinx Research

Scaling Convolutional Neural Networks on Reconfigurable Logic Michaela Blott, Principal Engineer, Xilinx Research Scaling Convolutional Neural Networks on Reconfigurable Logic Michaela Blott, Principal Engineer, Xilinx Research Nick Fraser (Xilinx & USydney) Yaman Umuroglu (Xilinx & NTNU) Giulio Gambardella (Xilinx)

More information

CNN optimization. Rassadin A

CNN optimization. Rassadin A CNN optimization Rassadin A. 01.2017-02.2017 What to optimize? Training stage time consumption (CPU / GPU) Inference stage time consumption (CPU / GPU) Training stage memory consumption Inference stage

More information

Computer Vision Lecture 16

Computer Vision Lecture 16 Computer Vision Lecture 16 Deep Learning Applications 11.01.2017 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Announcements Seminar registration period starts

More information

Deep learning for object detection. Slides from Svetlana Lazebnik and many others

Deep learning for object detection. Slides from Svetlana Lazebnik and many others Deep learning for object detection Slides from Svetlana Lazebnik and many others Recent developments in object detection 80% PASCAL VOC mean0average0precision0(map) 70% 60% 50% 40% 30% 20% 10% Before deep

More information

Supplementary material for Analyzing Filters Toward Efficient ConvNet

Supplementary material for Analyzing Filters Toward Efficient ConvNet Supplementary material for Analyzing Filters Toward Efficient Net Takumi Kobayashi National Institute of Advanced Industrial Science and Technology, Japan takumi.kobayashi@aist.go.jp A. Orthonormal Steerable

More information

INTRODUCTION TO DEEP LEARNING

INTRODUCTION TO DEEP LEARNING INTRODUCTION TO DEEP LEARNING CONTENTS Introduction to deep learning Contents 1. Examples 2. Machine learning 3. Neural networks 4. Deep learning 5. Convolutional neural networks 6. Conclusion 7. Additional

More information

On Classification: An Empirical Study of Existing Algorithms Based on Two Kaggle Competitions

On Classification: An Empirical Study of Existing Algorithms Based on Two Kaggle Competitions On Classification: An Empirical Study of Existing Algorithms Based on Two Kaggle Competitions CAMCOS Report Day December 9th, 2015 San Jose State University Project Theme: Classification The Kaggle Competition

More information

Machine Learning Workshop

Machine Learning Workshop Machine Learning Workshop {Presenters} Feb. 20th, 2018 Theory of Neural Networks Architecture and Types of Layers: Fully Connected (FC) Convolutional Neural Network (CNN) Pooling Drop out Residual Recurrent

More information

Hide-and-Seek: Forcing a network to be Meticulous for Weakly-supervised Object and Action Localization

Hide-and-Seek: Forcing a network to be Meticulous for Weakly-supervised Object and Action Localization Hide-and-Seek: Forcing a network to be Meticulous for Weakly-supervised Object and Action Localization Krishna Kumar Singh and Yong Jae Lee University of California, Davis ---- Paper Presentation Yixian

More information

Deep Learning Workshop. Nov. 20, 2015 Andrew Fishberg, Rowan Zellers

Deep Learning Workshop. Nov. 20, 2015 Andrew Fishberg, Rowan Zellers Deep Learning Workshop Nov. 20, 2015 Andrew Fishberg, Rowan Zellers Why deep learning? The ImageNet Challenge Goal: image classification with 1000 categories Top 5 error rate of 15%. Krizhevsky, Alex,

More information

Fei-Fei Li & Justin Johnson & Serena Yeung

Fei-Fei Li & Justin Johnson & Serena Yeung Lecture 9-1 Administrative A2 due Wed May 2 Midterm: In-class Tue May 8. Covers material through Lecture 10 (Thu May 3). Sample midterm released on piazza. Midterm review session: Fri May 4 discussion

More information

Deep Face Recognition. Nathan Sun

Deep Face Recognition. Nathan Sun Deep Face Recognition Nathan Sun Why Facial Recognition? Picture ID or video tracking Higher Security for Facial Recognition Software Immensely useful to police in tracking suspects Your face will be an

More information

Investigation of Machine Learning Algorithm Compared to Fuzzy Logic in Wild Fire Smoke Detection Applications

Investigation of Machine Learning Algorithm Compared to Fuzzy Logic in Wild Fire Smoke Detection Applications Investigation of Machine Learning Algorithm Compared to Fuzzy Logic in Wild Fire Smoke Detection Applications Azarm Nowzad, Andreas Jock, Klaus Jäckel IQ wireless GmbH, Berlin, Germany Azarm Nowzad, Ralf

More information

Convolution Neural Networks for Chinese Handwriting Recognition

Convolution Neural Networks for Chinese Handwriting Recognition Convolution Neural Networks for Chinese Handwriting Recognition Xu Chen Stanford University 450 Serra Mall, Stanford, CA 94305 xchen91@stanford.edu Abstract Convolutional neural networks have been proven

More information

Project 3 Q&A. Jonathan Krause

Project 3 Q&A. Jonathan Krause Project 3 Q&A Jonathan Krause 1 Outline R-CNN Review Error metrics Code Overview Project 3 Report Project 3 Presentations 2 Outline R-CNN Review Error metrics Code Overview Project 3 Report Project 3 Presentations

More information

Object Detection Lecture Introduction to deep learning (CNN) Idar Dyrdal

Object Detection Lecture Introduction to deep learning (CNN) Idar Dyrdal Object Detection Lecture 10.3 - Introduction to deep learning (CNN) Idar Dyrdal Deep Learning Labels Computational models composed of multiple processing layers (non-linear transformations) Used to learn

More information

CMU Lecture 18: Deep learning and Vision: Convolutional neural networks. Teacher: Gianni A. Di Caro

CMU Lecture 18: Deep learning and Vision: Convolutional neural networks. Teacher: Gianni A. Di Caro CMU 15-781 Lecture 18: Deep learning and Vision: Convolutional neural networks Teacher: Gianni A. Di Caro DEEP, SHALLOW, CONNECTED, SPARSE? Fully connected multi-layer feed-forward perceptrons: More powerful

More information

Unsupervised learning in Vision

Unsupervised learning in Vision Chapter 7 Unsupervised learning in Vision The fields of Computer Vision and Machine Learning complement each other in a very natural way: the aim of the former is to extract useful information from visual

More information

Lecture 12: Model Serving. CSE599W: Spring 2018

Lecture 12: Model Serving. CSE599W: Spring 2018 Lecture 12: Model Serving CSE599W: Spring 2018 Deep Learning Applications That drink will get you to 2800 calories for today I last saw your keys in the store room Remind Tom of the party You re on page

More information

arxiv: v1 [cs.lg] 31 Oct 2018

arxiv: v1 [cs.lg] 31 Oct 2018 UNDERSTANDING DEEP NEURAL NETWORKS USING TOPOLOGICAL DATA ANALYSIS DANIEL GOLDFARB arxiv:1811.00852v1 [cs.lg] 31 Oct 2018 Abstract. Deep neural networks (DNN) are black box algorithms. They are trained

More information

Encoder-Decoder Networks for Semantic Segmentation. Sachin Mehta

Encoder-Decoder Networks for Semantic Segmentation. Sachin Mehta Encoder-Decoder Networks for Semantic Segmentation Sachin Mehta Outline > Overview of Semantic Segmentation > Encoder-Decoder Networks > Results What is Semantic Segmentation? Input: RGB Image Output:

More information

Machine Learning 13. week

Machine Learning 13. week Machine Learning 13. week Deep Learning Convolutional Neural Network Recurrent Neural Network 1 Why Deep Learning is so Popular? 1. Increase in the amount of data Thanks to the Internet, huge amount of

More information

The exam is closed book, closed notes except your one-page cheat sheet.

The exam is closed book, closed notes except your one-page cheat sheet. CS 189 Fall 2015 Introduction to Machine Learning Final Please do not turn over the page before you are instructed to do so. You have 2 hours and 50 minutes. Please write your initials on the top-right

More information

Bilevel Sparse Coding

Bilevel Sparse Coding Adobe Research 345 Park Ave, San Jose, CA Mar 15, 2013 Outline 1 2 The learning model The learning algorithm 3 4 Sparse Modeling Many types of sensory data, e.g., images and audio, are in high-dimensional

More information

SHIV SHAKTI International Journal in Multidisciplinary and Academic Research (SSIJMAR) Vol. 7, No. 2, April 2018 (ISSN )

SHIV SHAKTI International Journal in Multidisciplinary and Academic Research (SSIJMAR) Vol. 7, No. 2, April 2018 (ISSN ) SHIV SHAKTI International Journal in Multidisciplinary and Academic Research (SSIJMAR) Vol. 7, No. 2, April 2018 (ISSN 2278 5973) Facial Recognition Using Deep Learning Rajeshwar M, Sanjit Singh Chouhan,

More information

Video Object Segmentation using Deep Learning

Video Object Segmentation using Deep Learning Video Object Segmentation using Deep Learning Update Presentation, Week 3 Zack While Advised by: Rui Hou, Dr. Chen Chen, and Dr. Mubarak Shah June 2, 2017 Youngstown State University 1 Table of Contents

More information

3D model classification using convolutional neural network

3D model classification using convolutional neural network 3D model classification using convolutional neural network JunYoung Gwak Stanford jgwak@cs.stanford.edu Abstract Our goal is to classify 3D models directly using convolutional neural network. Most of existing

More information

CENG 783. Special topics in. Deep Learning. AlchemyAPI. Week 11. Sinan Kalkan

CENG 783. Special topics in. Deep Learning. AlchemyAPI. Week 11. Sinan Kalkan CENG 783 Special topics in Deep Learning AlchemyAPI Week 11 Sinan Kalkan TRAINING A CNN Fig: http://www.robots.ox.ac.uk/~vgg/practicals/cnn/ Feed-forward pass Note that this is written in terms of the

More information