Deep Learning intro and hands-on tutorial

Size: px
Start display at page:

Download "Deep Learning intro and hands-on tutorial"

Transcription

1 Deep Learning intro and hands-on tutorial Π Ε. ώ Π ώ. Π ΠΘ 1 / 53

2 Deep Learning 2 / 53

3 Δ Έ ( ) ω π μ, ώπ ώ π ω (,...), π ώ π π π π ω ω ώπ ώ π, (biologically plausible) Δ π ώώ π ώ Ε π θ! 3 / 53

4 Ε π Δ 3 main ingredients! ( Δ ) Δ ώ (loss/objective function) 4 / 53

5 1943: Π ώ θ ώ ώ (Warren McCulloch and Walter Pitts) : Π π π θ π ώ ( neuroscience-oriented) 1958: Perceptron (Frank Rosenblatt) 1975: Backpropagation : ώ π π ώ π π π Ο ώ (π.. SVMs) θ ώ π π π π ώ Δ π π ώ Δ π ώ 5 / 53

6 2000-Σ μ : Deep Learning π state-of-the-art π π tasks Χ ώ π ώ π π π μ ώ (GPUs) π π π ώ Μ π μ ω θ ώ π (big data) Ν μ π (relu, Adam,...) 6 / 53

7 Ε ώ 7 / 53

8 8 / 53

9 9 / 53

10 Deep Learning A π ώ Π ( ώ ) π information retrieval routing algorithms... Data mining, analytics,... Έ π π valuable skills ώ 10 / 53

11 Deep Learning Startups Affectiva (emotion recognition from videos or images) Gridspace (Conversationally-aware software, speech recognition, speaker identification, critical moment) 11 / 53

12 Deep Learning Startups Ditto Labs (brand identification) Nervana (silicon to software optimized framework for deep learning) Finance, energy, online services, / 53

13 Deep Learning Startups Deep Genomics (precision medicine, understanding diseases, developing genetic therapies) Indico (text+image analytics for developing new products) 13 / 53

14 Deep Learning Startups Enlitic (medical image analysis) Deep Instinct ( cybersecurity, detects, predicts and prevents advanced persistent threats in real time) MarianaIQ (B2B account-based marketing) 14 / 53

15 Deep Learning Η π π ώ θ Perceptron: 15 / 53

16 Deep Learning 2-layer MLP: 16 / 53

17 Deep Learning 3-layer MLP: 17 / 53

18 Deep Learning LeNet: 18 / 53

19 Deep Learning GoogleLeNet: ResNet-200: 200 layers / 53

20 π Δ From scratch (C, Java,...) MATLAB Ε ώ π π π π π (Deep Learning Frameworks) Torch, Theano, Tensorflow,... Caffe, CNTK, Darkenet,... π π Python 20 / 53

21 ώ π π Framework? Η π π π ώ π π π π ώ, π Η ώ π Δ ώ ώ GPUs π deployment ώ ώ π.. CUDA Έ ώ π ώ Έ ώ ώ (π π ) 21 / 53

22 GPU Computing Ο GPUs π ώ hardware π ώ ώ π π π ώ π π (π.. π ώώ, convolutions,...) π ώ Δ π π Η nvidia ώ π GPU computing ώ ( ώ, π.. bitcoin mining) 22 / 53

23 GPU Computing Ο π ώώ ώ π θ GPU θ π θ π (cublas, curand, cudnn,... ) θ ώ π π wrapper θ π π π (π.. python) Ε (ResNet-200, forward+backward pass): Dual Xeon E v3: ms Titan X (Pascal): 297 ms 75 π GPU π π θ ώ, ώ ώ. 23 / 53

24 GPU Computing Δ ώ π, deployment! Ο π π ώ ώ ώ π GPU-accelerated hardware (π.x. self-driving cars) 24 / 53

25 DL Frameworks 25 / 53

26 Deep Learning Frameworks Π π! Caffe CTNK Tensorflow Darknet Theano (Py)Torch Keras, Blocks, Lasagne, 26 / 53

27 Caffe π π GPU-accelerated θ Deep Learning π ώ π θ ώ ω π μμ μ Η μ π ώ ώ Δ π C++ Python Π μ ω image analysis Χ π projects large-scale μπ μ Caffe2 (supported by Facebook) 27 / 53

28 Tensorflow Google supported! Η μ ώ Π distributed Yπ mobile Π ώ π APIs π (Python, C++, Java,...) Όώ : Π π π π π Π ώ 28 / 53

29 CTNK Microsoft Cognitive Toolkit (CNTK) Ε μ μ π ω μ ω Π π ώ deployment APIs C++, Python, C# 29 / 53

30 Darknet Lightweight minimal framework ώώ C CUDA π π ώ ώ Δ π ( ) π π minimal dependencies ( ) π ώ, θ, 30 / 53

31 Theano θ ώώ Python Π ώ π ώ θ ώ Ο ώ ώ (ώ θ ώ ) Theano ώ : π ώ ώ π π (C) π π π π π CUDA GPU π handler python Large compilation cost, fast execution 31 / 53

32 PyTorch Π ώ Torch Python π ώ θ π π μ ( ώπ ) Π ώ ( ώ ώπ ώ π θ π Caffe/Caffe2) π π π GPU Π ώ π ώ ώ π 32 / 53

33 θ /Wrappers Π π π π π GPUs π deep learning models π θ π π π π Keras (Tensorflow, Theano, CTNK) Lasagne (Theano) Blocks (Theano) 33 / 53

34 Pre-trained models Η π ώ ώ π π ώ θ ώ π ώ π ώ ώ π ώ workstations ώ 4 high end π π frameworks π ώ pretrained ώ π ώ π internet ώ π 34 / 53

35 Π Framework ώ? Π! π ώ π θώ? Δ θ ώ π ώ? Π θ ώ? Ε? Deployment target? Χ pretrained models? 35 / 53

36 Darknet 36 / 53

37 Darknet Ε π π ώ π state-of-the-art π ώ pretrained ώ Ε ( Linux) π ώ π θ ώ 37 / 53

38 ώ ώ π pretrained ώ ώ (yolo-tiny, yolo, coco-tiny, coco-tiny) Η COCO ώ ώ ώ π π π π ώ / 53

39 ώ./darknet coco test cfg/yolo-coco.cfg data/yolo-coco.weights image.jpg 39 / 53

40 ώ predictions.png 40 / 53

41 Deep Dream (nightmares)./darknet-gpu nightmare cfg/vgg-conv.cfg data/vgg-conv.weights image.jpg 5 41 / 53

42 Deep Dream (nightmares)./darknet-gpu nightmare cfg/vgg-conv.cfg data/vgg-conv.weights image.jpg 8 42 / 53

43 Deep Dream (nightmares)./darknet-gpu nightmare cfg/vgg-conv.cfg data/vgg-conv.weights image.jpg / 53

44 Deep Dream (nightmares)./darknet-gpu nightmare cfg/vgg-conv.cfg data/vgg-conv.weights image.jpg / 53

45 RNN text generation./darknet rnn generate cfg/rnn.cfg data/shakespeare.weights -srand 0 -seed Hello there! -len Hello there! There s a good f r i e n d. 2 COUNTESS. I am sure you can ; you have a d e v i l were made on 3 her beauty, and the very night than he two f i g u r e s 4 the worthy Achalle, and you s h a l l make such a messenger. 5 I have not s i n g l e d on the f i e l d ; 6 The name o f Caesar s sun, when you should speak, 7 Which when they would be reveng d on him in t h e i r death 8 But t h a t I have r e c e i v d and say they 9 Had s t r a n g e l y to his kingdom, and give her, 10 Upon the f i r s t here are both beams to love. 45 / 53

46 Keras 46 / 53

47 Keras θ Python π backend Tensorflow (default), theano CTNK Ε pip install keras Ε backend (edit Α/.keras/keras.json) 47 / 53

48 Keras Π π ώ well-known datasets (π.. MNIST) 1 from keras. d a t a s e t s import mnist datasets ώ pre-processing 1 ( x_train, y _ t r a i n ), ( x _ t e s t, y _ t e s t ) = mnist. load_data ( ) 2 x _ t r a i n = x _ t r a i n. reshape (60000, 784) 3 x _ t e s t = x _ t e s t. reshape (10000, 784) 4 x _ t r a i n = x _ t r a i n. astype ( f l o a t 3 2 ) / x _ t e s t = x _ t e s t. astype ( f l o a t 3 2 ) / keras π utilities ώ tasks (π.. ώ π labels binary ) 1 y _ t r a i n = keras. u t i l s. t o _ c a t e g o r i c a l ( y_train, 10) 2 y _ t e s t = keras. u t i l s. t o _ c a t e g o r i c a l ( y _ t e s t, 10) 48 / 53

49 Neural Networks in less than 10 lines Model Definition 1 model = S e q u e n t i a l ( ) 2 model. add ( Dense (512, a c t i v a t i o n = r e l u, input_shape =(784,) ) ) 3 model. add ( Dropout ( 0. 2 ) ) 4 model. add ( Dense (512, a c t i v a t i o n = r e l u ) ) 5 model. add ( Dropout ( 0. 2 ) ) 6 model. add ( Dense (10, a c t i v a t i o n = softmax ) ) 7 model. compile ( l o s s = c a t e g o r i c a l _ c r o s s e n t r o p y, optimizer=adam( ), metrics =[ accuracy ] ) Training 1 h i s t o r y = model. f i t ( x_train, y_train, b a t c h _ s i z e =128, epochs =10, verbose =2, v a l i d a t i o n _ d a t a =( x _ t e s t, y _ t e s t ) ) Testing 1 score = model. e v aluate ( x _ t e s t, y _ t e s t, verbose =0) 49 / 53

50 Neural Networks in less than 10 lines θ default θώ ώ θ! 1 model. compile ( l o s s = c a t e g o r i c a l _ c r o s s e n t r o p y, optimizer=adam( l r =0.01), m etrics =[ accuracy ] ) learning rate epoch 1 epoch 5 epoch % 96.91% 97.83% % 97.95% 98.02% % 96.04% 96.67% % % 10.09% GPU vs CPU i (4 cores, 32 bit): 19s per epoch Geforce 1060: 2s per epoch 50 / 53

51 CNN in less than 10 lines Model Definition 1 model = S e q u e n t i a l ( ) 2 model. add (Conv2D(32, k e r n e l _ s i z e =(3, 3), a c t i v a t i o n = r e l u, input_shape=input_shape ) ) 3 model. add (Conv2D(64, ( 3, 3), a c t i v a t i o n = r e l u ) ) 4 model. add ( MaxPooling2D ( p o o l _ s i z e =(2, 2) ) ) 5 model. add ( Dropout (0.25) ) 6 model. add ( F l a t t e n ( ) ) 7 model. add ( Dense (128, a c t i v a t i o n = r e l u ) ) 8 model. add ( Dropout ( 0. 5 ) ) 9 model. add ( Dense ( num_classes, a c t i v a t i o n = softmax ) ) 51 / 53

52 MLP vs CNN GPU vs CPU i (4 cores, 32 bit): 157s per epoch Geforce 1060: 14s per epoch ώ MLP CNN MLP: 98.02% (2s per epoch) CNN: 99.19% (14s per epoch) 10 π 52 / 53

53 Ε! 53 / 53

PATTERN RECOGNITION AND MACHINE LEARNING

PATTERN RECOGNITION AND MACHINE LEARNING PATTERN RECOGNITION AND MACHINE LEARNING Slide Set 6: Neural Networks and Deep Learning January 2018 Heikki Huttunen heikki.huttunen@tut.fi Department of Signal Processing Tampere University of Technology

More information

A Practitioner s Guide to MXNet

A Practitioner s Guide to MXNet 1/34 A Practitioner s Guide to MXNet Xingjian Shi Hong Kong University of Science and Technology (HKUST) HKUST CSE Seminar, March 31st, 2017 2/34 Outline 1 Introduction Deep Learning Basics MXNet Highlights

More information

Neural networks (NN) 1

Neural networks (NN) 1 Neural networks (NN) 1 Hedibert F. Lopes Insper Institute of Education and Research São Paulo, Brazil 1 Slides based on Chapter 11 of Hastie, Tibshirani and Friedman s book The Elements of Statistical

More information

Deep Learning: Pre- Requisites. Understanding gradient descent, autodiff, and softmax

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

More information

Outline. Overview CNTK introduction. Educational resources Conclusions. Symbolic loop Batch scheduling Data parallel training

Outline. Overview CNTK introduction. Educational resources Conclusions. Symbolic loop Batch scheduling Data parallel training Outline Overview CNTK introduction Symbolic loop Batch scheduling Data parallel training Educational resources Conclusions Outline Overview CNTK introduction Symbolic loop Batch scheduling Data parallel

More information

Neural Networks and Deep Learning

Neural Networks and Deep Learning Neural Networks and Deep Learning Professor Ameet Talwalkar November 12, 2015 Professor Ameet Talwalkar Neural Networks and Deep Learning November 12, 2015 1 / 16 Outline 1 Review of last lecture AdaBoost

More information

Pytorch Tutorial. Xiaoyong Yuan, Xiyao Ma 2018/01

Pytorch Tutorial. Xiaoyong Yuan, Xiyao Ma 2018/01 (Li Lab) National Science Foundation Center for Big Learning (CBL) Department of Electrical and Computer Engineering (ECE) Department of Computer & Information Science & Engineering (CISE) Pytorch Tutorial

More information

Grundlagen der Künstlichen Intelligenz

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

More information

Apprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning

Apprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning Apprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning Nicolas Thome Prenom.Nom@cnam.fr http://cedric.cnam.fr/vertigo/cours/ml2/ Département Informatique Conservatoire

More information

Deep Learning Lecture 2

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

More information

Quantum Artificial Intelligence and Machine Learning: The Path to Enterprise Deployments. Randall Correll. +1 (703) Palo Alto, CA

Quantum Artificial Intelligence and Machine Learning: The Path to Enterprise Deployments. Randall Correll. +1 (703) Palo Alto, CA Quantum Artificial Intelligence and Machine : The Path to Enterprise Deployments Randall Correll randall.correll@qcware.com +1 (703) 867-2395 Palo Alto, CA 1 Bundled software and services Professional

More information

Hands-on Lab: Deep Learning with the Theano Python Library

Hands-on Lab: Deep Learning with the Theano Python Library Hands-on Lab: Deep Learning with the Python Library Frédéric Bastien Montreal Institute for Learning Algorithms Université de Montréal Montréal, Canada bastienf@iro.umontreal.ca Presentation prepared with

More information

Memory-Augmented Attention Model for Scene Text Recognition

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

More information

DEEP LEARNING AND NEURAL NETWORKS: BACKGROUND AND HISTORY

DEEP LEARNING AND NEURAL NETWORKS: BACKGROUND AND HISTORY DEEP LEARNING AND NEURAL NETWORKS: BACKGROUND AND HISTORY 1 On-line Resources http://neuralnetworksanddeeplearning.com/index.html Online book by Michael Nielsen http://matlabtricks.com/post-5/3x3-convolution-kernelswith-online-demo

More information

Machine Learning for Gravitational Wave signals classification in LIGO and Virgo

Machine Learning for Gravitational Wave signals classification in LIGO and Virgo Machine Learning for Gravitational Wave signals classification in LIGO and Virgo Elena Cuoco European Gravitational Observatory www.elenacuoco.com @elenacuoco 2 About me About me Working as Data Analyst

More information

Introduction to Neural Networks

Introduction to Neural Networks CUONG TUAN NGUYEN SEIJI HOTTA MASAKI NAKAGAWA Tokyo University of Agriculture and Technology Copyright by Nguyen, Hotta and Nakagawa 1 Pattern classification Which category of an input? Example: Character

More information

Artificial Neural Networks. Introduction to Computational Neuroscience Tambet Matiisen

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

More information

DANIEL WILSON AND BEN CONKLIN. Integrating AI with Foundation Intelligence for Actionable Intelligence

DANIEL WILSON AND BEN CONKLIN. Integrating AI with Foundation Intelligence for Actionable Intelligence DANIEL WILSON AND BEN CONKLIN Integrating AI with Foundation Intelligence for Actionable Intelligence INTEGRATING AI WITH FOUNDATION INTELLIGENCE FOR ACTIONABLE INTELLIGENCE in an arms race for artificial

More information

Averaging Points. What s the average of P and Q? v = Q - P. P + 0.5v = P + 0.5(Q P) = 0.5P Q

Averaging Points. What s the average of P and Q? v = Q - P. P + 0.5v = P + 0.5(Q P) = 0.5P Q Linear Perceptron Averaging Points What s the average of P and Q? v = Q - P P Q P + 0.5v = P + 0.5(Q P) = 0.5P + 0.5 Q Averaging Points What s the average of P and Q? v = Q - P P Q Linear Interpolation

More information

Supervised Deep Learning

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

More information

Learning Deep Architectures for AI. Part II - Vijay Chakilam

Learning Deep Architectures for AI. Part II - Vijay Chakilam Learning Deep Architectures for AI - Yoshua Bengio Part II - Vijay Chakilam Limitations of Perceptron x1 W, b 0,1 1,1 y x2 weight plane output =1 output =0 There is no value for W and b such that the model

More information

Deep Learning In An Afternoon

Deep Learning In An Afternoon Deep Learning In An Afternoon John Urbanic Parallel Computing Scientist Pittsburgh Supercomputing Center Copyright 2018 Deep Learning / Neural Nets Without question the biggest thing in ML and computer

More information

Neural Networks. Yan Shao Department of Linguistics and Philology, Uppsala University 7 December 2016

Neural Networks. Yan Shao Department of Linguistics and Philology, Uppsala University 7 December 2016 Neural Networks Yan Shao Department of Linguistics and Philology, Uppsala University 7 December 2016 Outline Part 1 Introduction Feedforward Neural Networks Stochastic Gradient Descent Computational Graph

More information

CNTK Microsoft s Open Source Deep Learning Toolkit. Taifeng Wang Lead Researcher, Microsoft Research Asia 2016 GTC China

CNTK Microsoft s Open Source Deep Learning Toolkit. Taifeng Wang Lead Researcher, Microsoft Research Asia 2016 GTC China CNTK Microsoft s Open Source Deep Learning Toolkit Taifeng Wang Lead Researcher, Microsoft Research Asia 2016 GTC China Deep learning in Microsoft Cognitive Services https://how-old.net http://www.captionbot.ai

More information

Based on the original slides of Hung-yi Lee

Based on the original slides of Hung-yi Lee Based on the original slides of Hung-yi Lee Google Trends Deep learning obtains many exciting results. Can contribute to new Smart Services in the Context of the Internet of Things (IoT). IoT Services

More information

Deep Learning Lecture 2

Deep Learning Lecture 2 Fall 2015 Deep Learning CMPSCI 697L Deep Learning Lecture 2 Sridhar Mahadevan Autonomous Learning Lab UMass Amherst COLLEGE Outline Some topics to be covered: 1. Quick review of classic neural nets, single

More information

MagmaDNN High-Performance Data Analytics for Manycore GPUs and CPUs

MagmaDNN High-Performance Data Analytics for Manycore GPUs and CPUs MagmaDNN High-Performance Data Analytics for Manycore GPUs and CPUs Lucien Ng The Chinese University of Hong Kong Kwai Wong The Joint Institute for Computational Sciences (JICS), UTK and ORNL Azzam Haidar,

More information

Binary Deep Learning. Presented by Roey Nagar and Kostya Berestizshevsky

Binary Deep Learning. Presented by Roey Nagar and Kostya Berestizshevsky Binary Deep Learning Presented by Roey Nagar and Kostya Berestizshevsky Deep Learning Seminar, School of Electrical Engineering, Tel Aviv University January 22 nd 2017 Lecture Outline Motivation and existing

More information

Neural Networks. Intro to AI Bert Huang Virginia Tech

Neural Networks. Intro to AI Bert Huang Virginia Tech Neural Networks Intro to AI Bert Huang Virginia Tech Outline Biological inspiration for artificial neural networks Linear vs. nonlinear functions Learning with neural networks: back propagation https://en.wikipedia.org/wiki/neuron#/media/file:chemical_synapse_schema_cropped.jpg

More information

Deep Learning Autoencoder Models

Deep Learning Autoencoder Models Deep Learning Autoencoder Models Davide Bacciu Dipartimento di Informatica Università di Pisa Intelligent Systems for Pattern Recognition (ISPR) Generative Models Wrap-up Deep Learning Module Lecture Generative

More information

Deep Learning (CNNs)

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

More information

Neural Networks. David Rosenberg. July 26, New York University. David Rosenberg (New York University) DS-GA 1003 July 26, / 35

Neural Networks. David Rosenberg. July 26, New York University. David Rosenberg (New York University) DS-GA 1003 July 26, / 35 Neural Networks David Rosenberg New York University July 26, 2017 David Rosenberg (New York University) DS-GA 1003 July 26, 2017 1 / 35 Neural Networks Overview Objectives What are neural networks? How

More information

Course Structure. Psychology 452 Week 12: Deep Learning. Chapter 8 Discussion. Part I: Deep Learning: What and Why? Rufus. Rufus Processed By Fetch

Course Structure. Psychology 452 Week 12: Deep Learning. Chapter 8 Discussion. Part I: Deep Learning: What and Why? Rufus. Rufus Processed By Fetch Psychology 452 Week 12: Deep Learning What Is Deep Learning? Preliminary Ideas (that we already know!) The Restricted Boltzmann Machine (RBM) Many Layers of RBMs Pros and Cons of Deep Learning Course Structure

More information

Convolutional Neural Nets

Convolutional Neural Nets Convolutional Neural Nets Oliver Dürr Datalab-Lunch Seminar Series Winterthur, 17 December 2014 1 History of CNN 1980 Kunihiko Fukushima introduction 1998 Le Cunn (Backpropagation) Schmidt Huber Group

More information

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 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

More information

Tao Mei, Senior Researcher Cha Zhang, Principal Applied Science Manager Microsoft AI & Research

Tao Mei, Senior Researcher Cha Zhang, Principal Applied Science Manager Microsoft AI & Research Tao Mei, Senior Researcher Cha Zhang, Principal Applied Science Manager Microsoft AI & Research Agenda Introduction for Cognitive Toolkit (Cha) CNTK overview CNTK for image/video tasks Break Intelligent

More information

The Changing Landscape of Land Administration

The Changing Landscape of Land Administration The Changing Landscape of Land Administration B r e n t J o n e s P E, PLS E s r i World s Largest Media Company No Journalists No Content Producers No Photographers World s Largest Hospitality Company

More information

AMLD Deep Learning in PyTorch. 2. PyTorch tensors

AMLD Deep Learning in PyTorch. 2. PyTorch tensors AMLD Deep Learning in PyTorch 2. PyTorch tensors François Fleuret http://fleuret.org/amld/ February 10, 2018 ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNE PyTorch s tensors François Fleuret AMLD Deep Learning

More information

Convolutional Neural Networks

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»

More information

NLP Homework: Dependency Parsing with Feed-Forward Neural Network

NLP Homework: Dependency Parsing with Feed-Forward Neural Network NLP Homework: Dependency Parsing with Feed-Forward Neural Network Submission Deadline: Monday Dec. 11th, 5 pm 1 Background on Dependency Parsing Dependency trees are one of the main representations used

More information

EIE6207: Deep Learning and Deep Neural Networks

EIE6207: Deep Learning and Deep Neural Networks EIE6207: Deep Learning and Deep Neural Networs Man-Wai MAK Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University enmwma@polyu.edu.h http://www.eie.polyu.edu.h/ mwma References:

More information

introduction to convolutional networks using tensorflow

introduction to convolutional networks using tensorflow introduction to convolutional networks using tensorflow Jesús Fernández Bes, jfbes@ing.uc3m.es 8 de febrero de 2016 contents Install What is Tensorflow? Implementing Softmax Regression Deep Convolutional

More information

Deep Learning: a gentle introduction

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

More information

Introduction to Deep Learning CMPT 733. Steven Bergner

Introduction to Deep Learning CMPT 733. Steven Bergner Introduction to Deep Learning CMPT 733 Steven Bergner Overview Renaissance of artificial neural networks Representation learning vs feature engineering Background Linear Algebra, Optimization Regularization

More information

Introduction to Deep Learning

Introduction to Deep Learning Introduction to Deep Learning A. G. Schwing & S. Fidler University of Toronto, 2015 A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding 2015 1 / 39 Outline 1 Universality of Neural Networks

More information

Deep Learning In An Afternoon

Deep Learning In An Afternoon Deep Learning In An Afternoon John Urbanic Parallel Computing Scientist Pittsburgh Supercomputing Center Copyright 2017 Deep Learning / Neural Nets Without question the biggest thing in ML and computer

More information

Jakub Hajic Artificial Intelligence Seminar I

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

More information

Introduction to Convolutional Neural Networks 2018 / 02 / 23

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

More information

TTIC 31230, Fundamentals of Deep Learning, Winter David McAllester. The Fundamental Equations of Deep Learning

TTIC 31230, Fundamentals of Deep Learning, Winter David McAllester. The Fundamental Equations of Deep Learning TTIC 31230, Fundamentals of Deep Learning, Winter 2019 David McAllester The Fundamental Equations of Deep Learning 1 Early History 1943: McCullock and Pitts introduced the linear threshold neuron. 1962:

More information

Development of Uncertainty-Guided Deep Learning with Application to Thermal Fluid Closures

Development of Uncertainty-Guided Deep Learning with Application to Thermal Fluid Closures Development of Uncertainty-Guided Deep Learning with Application to Thermal Fluid Closures Chih-Wei Chang, Nam Dinh NEKVAC/NUC Workshop Multiphysics Model Validation June 27-29, 2017 Outline Introduction

More information

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 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

More information

Deep Residual. Variations

Deep Residual. Variations Deep Residual Network and Its Variations Diyu Yang (Originally prepared by Kaiming He from Microsoft Research) Advantages of Depth Degradation Problem Possible Causes? Vanishing/Exploding Gradients. Overfitting

More information

Introduction to Convolutional Neural Networks (CNNs)

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

More information

TensorFlow: A Framework for Scalable Machine Learning

TensorFlow: A Framework for Scalable Machine Learning TensorFlow: A Framework for Scalable Machine Learning You probably Outline want to know... What is TensorFlow? Why did we create TensorFlow? How does Tensorflow Work? Example: Linear Regression Example:

More information

Formal neuron (with bias)

Formal neuron (with bias) Formal neuron (with bias) 1 bias threshold x 0 = 1 w 0 = h y σ ξ w 1 w 2 w n x 1 x 2 x n x 0 = 1, x 1,..., x n R are inputs w 0, w 1,..., w n R are weights ξ is an inner potential; almost always ξ = w

More information

Regression Adjustment with Artificial Neural Networks

Regression Adjustment with Artificial Neural Networks Regression Adjustment with Artificial Neural Networks Age of Big Data: data comes in a rate and in a variety of types that exceed our ability to analyse it Texts, image, speech, video Real motivation:

More information

(Feed-Forward) Neural Networks Dr. Hajira Jabeen, Prof. Jens Lehmann

(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

More information

Tasks ADAS. Self Driving. Non-machine Learning. Traditional MLP. Machine-Learning based method. Supervised CNN. Methods. Deep-Learning based

Tasks ADAS. Self Driving. Non-machine Learning. Traditional MLP. Machine-Learning based method. Supervised CNN. Methods. Deep-Learning based UNDERSTANDING CNN 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

More information

Identifying QCD transition using Deep Learning

Identifying QCD transition using Deep Learning Identifying QCD transition using Deep Learning Kai Zhou Long-Gang Pang, Nan Su, Hannah Peterson, Horst Stoecker, Xin-Nian Wang Collaborators: arxiv:1612.04262 Outline 2 What is deep learning? Artificial

More information

Course 395: Machine Learning - Lectures

Course 395: Machine Learning - Lectures Course 395: Machine Learning - Lectures Lecture 1-2: Concept Learning (M. Pantic) Lecture 3-4: Decision Trees & CBC Intro (M. Pantic & S. Petridis) Lecture 5-6: Evaluating Hypotheses (S. Petridis) Lecture

More information

Index. Santanu Pattanayak 2017 S. Pattanayak, Pro Deep Learning with TensorFlow,

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

More information

Artificial neural networks

Artificial neural networks Artificial neural networks B. Mehlig, Department of Physics, University of Gothenburg, Sweden FFR35/FIM70 Artificial Neural Networks Chalmers/Gothenburg University, 7.5 credits 3 Course home page Teachers

More information

Deep learning on 3D geometries. Hope Yao Design Informatics Lab Department of Mechanical and Aerospace Engineering

Deep learning on 3D geometries. Hope Yao Design Informatics Lab Department of Mechanical and Aerospace Engineering Deep learning on 3D geometries Hope Yao Design Informatics Lab Department of Mechanical and Aerospace Engineering Overview Background Methods Numerical Result Future improvements Conclusion Background

More information

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) 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

More information

ECE521 W17 Tutorial 1. Renjie Liao & Min Bai

ECE521 W17 Tutorial 1. Renjie Liao & Min Bai ECE521 W17 Tutorial 1 Renjie Liao & Min Bai Schedule Linear Algebra Review Matrices, vectors Basic operations Introduction to TensorFlow NumPy Computational Graphs Basic Examples Linear Algebra Review

More information

Architecture Multilayer Perceptron (MLP)

Architecture Multilayer Perceptron (MLP) Architecture Multilayer Perceptron (MLP) 1 Output Hidden Input Neurons partitioned into layers; y 1 y 2 one input layer, one output layer, possibly several hidden layers layers numbered from 0; the input

More information

Introduction to Machine Learning (67577)

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

More information

Deep Learning. Convolutional Neural Networks Applications

Deep Learning. Convolutional Neural Networks Applications Deep Learning Using a Convolutional Neural Network Dr. Ing. Morris Riedel Adjunct Associated Professor School of Engineering and Natural Sciences, University of Iceland Research Group Leader, Juelich Supercomputing

More information

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 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

More information

(Artificial) Neural Networks in TensorFlow

(Artificial) Neural Networks in TensorFlow (Artificial) Neural Networks in TensorFlow By Prof. Seungchul Lee Industrial AI Lab http://isystems.unist.ac.kr/ POSTECH Table of Contents I. 1. Recall Supervised Learning Setup II. 2. Artificial Neural

More information

Translator

Translator Translator Marian Rejewski A few words about Marian Portable C++ code with minimal dependencies (CUDA or MKL and still Boost); Single engine for training and decoding on GPU and CPU; Custom auto-diff engine

More information

Deep Learning Lab Course 2017 (Deep Learning Practical)

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

More information

10. Artificial Neural Networks

10. Artificial Neural Networks Foundations of Machine Learning CentraleSupélec Fall 217 1. Artificial Neural Networks Chloé-Agathe Azencot Centre for Computational Biology, Mines ParisTech chloe-agathe.azencott@mines-paristech.fr Learning

More information

2017 Fall ECE 692/599: Binary Representation Learning for Large Scale Visual Data

2017 Fall ECE 692/599: Binary Representation Learning for Large Scale Visual Data 2017 Fall ECE 692/599: Binary Representation Learning for Large Scale Visual Data Liu Liu Instructor: Dr. Hairong Qi University of Tennessee, Knoxville lliu25@vols.utk.edu September 21, 2017 Liu Liu (UTK)

More information

Making Deep Learning Understandable for Analyzing Sequential Data about Gene Regulation

Making Deep Learning Understandable for Analyzing Sequential Data about Gene Regulation Making Deep Learning Understandable for Analyzing Sequential Data about Gene Regulation Dr. Yanjun Qi Department of Computer Science University of Virginia Tutorial @ ACM BCB-2018 8/29/18 Yanjun Qi / UVA

More information

Deep neural networks and fraud detection

Deep neural networks and fraud detection U.U.D.M. Project Report 2017:38 Deep neural networks and fraud detection Yifei Lu Examensarbete i matematik, 30 hp Handledare: Kaj Nyström Examinator: Erik Ekström Oktober 2017 Department of Mathematics

More information

Neural Network Tutorial & Application in Nuclear Physics. Weiguang Jiang ( 蒋炜光 ) UTK / ORNL

Neural Network Tutorial & Application in Nuclear Physics. Weiguang Jiang ( 蒋炜光 ) UTK / ORNL Neural Network Tutorial & Application in Nuclear Physics Weiguang Jiang ( 蒋炜光 ) UTK / ORNL Machine Learning Logistic Regression Gaussian Processes Neural Network Support vector machine Random Forest Genetic

More information

Dynamic Working Memory in Recurrent Neural Networks

Dynamic Working Memory in Recurrent Neural Networks Dynamic Working Memory in Recurrent Neural Networks Alexander Atanasov Research Advisor: John Murray Physics 471 Fall Term, 2016 Abstract Recurrent neural networks (RNNs) are physically-motivated models

More information

A Little History of Machine Learning

A Little History of Machine Learning 機器學習現在 過去 未來 A Little History of Machine Learning Chia-Ping Chen National Sun Yat-sen University @NPTU, December 2016 Outline ubiquitous machine intelligence challenge and reaction AI brief deep learning

More information

Artificial Neural Networks. Historical description

Artificial Neural Networks. Historical description Artificial Neural Networks Historical description Victor G. Lopez 1 / 23 Artificial Neural Networks (ANN) An artificial neural network is a computational model that attempts to emulate the functions of

More information

Recurrent Neural Networks (Part - 2) Sumit Chopra Facebook

Recurrent Neural Networks (Part - 2) Sumit Chopra Facebook Recurrent Neural Networks (Part - 2) Sumit Chopra Facebook Recap Standard RNNs Training: Backpropagation Through Time (BPTT) Application to sequence modeling Language modeling Applications: Automatic speech

More information

Administration. Registration Hw3 is out. Lecture Captioning (Extra-Credit) Scribing lectures. Questions. Due on Thursday 10/6

Administration. Registration Hw3 is out. Lecture Captioning (Extra-Credit) Scribing lectures. Questions. Due on Thursday 10/6 Administration Registration Hw3 is out Due on Thursday 10/6 Questions Lecture Captioning (Extra-Credit) Look at Piazza for details Scribing lectures With pay; come talk to me/send email. 1 Projects Projects

More information

Machine Learning for Physicists Lecture 1

Machine Learning for Physicists Lecture 1 Machine Learning for Physicists Lecture 1 Summer 2017 University of Erlangen-Nuremberg Florian Marquardt (Image generated by a net with 20 hidden layers) OUTPUT INPUT (Picture: Wikimedia Commons) OUTPUT

More information

Tutorial on Methods for Interpreting and Understanding Deep Neural Networks. Part 3: Applications & Discussion

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

More information

Deep Neural Networks

Deep Neural Networks Deep Neural Networks DT2118 Speech and Speaker Recognition Giampiero Salvi KTH/CSC/TMH giampi@kth.se VT 2015 1 / 45 Outline State-to-Output Probability Model Artificial Neural Networks Perceptron Multi

More information

APPLIED DEEP LEARNING PROF ALEXIEI DINGLI

APPLIED DEEP LEARNING PROF ALEXIEI DINGLI APPLIED DEEP LEARNING PROF ALEXIEI DINGLI TECH NEWS TECH NEWS HOW TO DO IT? TECH NEWS APPLICATIONS TECH NEWS TECH NEWS NEURAL NETWORKS Interconnected set of nodes and edges Designed to perform complex

More information

Land Cover Classification via Multitemporal Spatial Data by Deep Recurrent Neural Networks [Ienco17]

Land Cover Classification via Multitemporal Spatial Data by Deep Recurrent Neural Networks [Ienco17] Séminaire DL - AMAP 20/10/2017 Land Cover Classification via Multitemporal Spatial Data by Deep Recurrent Neural Networks [Ienco17] Dino Ienco, Raffaele Gaetano, Claire Dupaquier and Pierre Maurel Associated

More information

Neural Networks. Nicholas Ruozzi University of Texas at Dallas

Neural Networks. Nicholas Ruozzi University of Texas at Dallas Neural Networks Nicholas Ruozzi University of Texas at Dallas Handwritten Digit Recognition Given a collection of handwritten digits and their corresponding labels, we d like to be able to correctly classify

More information

Machine Learning. Neural Networks. (slides from Domingos, Pardo, others)

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

More information

Deep Learning in Action

Deep Learning in Action Deep Learning in Action Current state of AI In the early days of artificial intelligence, the field rapidly tackled and solved problems that are intellectually difficult for human beings but relatively

More information

Some Applications of Machine Learning to Astronomy. Eduardo Bezerra 20/fev/2018

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

More information

CSC Neural Networks. Perceptron Learning Rule

CSC Neural Networks. Perceptron Learning Rule CSC 302 1.5 Neural Networks Perceptron Learning Rule 1 Objectives Determining the weight matrix and bias for perceptron networks with many inputs. Explaining what a learning rule is. Developing the perceptron

More information

Finding Advanced Features for Housing Price Prediction

Finding Advanced Features for Housing Price Prediction Distributed Computing Finding Advanced Features for Housing Price Prediction Bachelor Thesis Ali Uzpak uzpaka@student.ethz.ch Distributed Computing Group Computer Engineering and Networks Laboratory ETH

More information

Demystifying deep learning. Artificial Intelligence Group Department of Computer Science and Technology, University of Cambridge, UK

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

More information

Faster Machine Learning via Low-Precision Communication & Computation. Dan Alistarh (IST Austria & ETH Zurich), Hantian Zhang (ETH Zurich)

Faster Machine Learning via Low-Precision Communication & Computation. Dan Alistarh (IST Austria & ETH Zurich), Hantian Zhang (ETH Zurich) Faster Machine Learning via Low-Precision Communication & Computation Dan Alistarh (IST Austria & ETH Zurich), Hantian Zhang (ETH Zurich) 2 How many bits do you need to represent a single number in machine

More information

Neural networks COMS 4771

Neural networks COMS 4771 Neural networks COMS 4771 1. Logistic regression Logistic regression Suppose X = R d and Y = {0, 1}. A logistic regression model is a statistical model where the conditional probability function has a

More information

ARTIFICIAL INTELLIGENCE. Artificial Neural Networks

ARTIFICIAL INTELLIGENCE. Artificial Neural Networks INFOB2KI 2017-2018 Utrecht University The Netherlands ARTIFICIAL INTELLIGENCE Artificial Neural Networks Lecturer: Silja Renooij These slides are part of the INFOB2KI Course Notes available from www.cs.uu.nl/docs/vakken/b2ki/schema.html

More information

HIGH PERFORMANCE CTC TRAINING FOR END-TO-END SPEECH RECOGNITION ON GPU

HIGH PERFORMANCE CTC TRAINING FOR END-TO-END SPEECH RECOGNITION ON GPU April 4-7, 2016 Silicon Valley HIGH PERFORMANCE CTC TRAINING FOR END-TO-END SPEECH RECOGNITION ON GPU Minmin Sun, NVIDIA minmins@nvidia.com April 5th Brief Introduction of CTC AGENDA Alpha/Beta Matrix

More information

Roadmap. Task and history System overview and results Human versus machine Cognitive Toolkit (CNTK) Summary and outlook. Microsoft Cognitive Toolkit

Roadmap. Task and history System overview and results Human versus machine Cognitive Toolkit (CNTK) Summary and outlook. Microsoft Cognitive Toolkit Roadmap Task and history System overview and results Human versus machine (CNTK) Summary and outlook Introduction: Task and History 4 The Human Parity Experiment Conversational telephone speech has been

More information

Introduction to (Convolutional) Neural Networks

Introduction to (Convolutional) Neural Networks Introduction to (Convolutional) Neural Networks Philipp Grohs Summer School DL and Vis, Sept 2018 Syllabus 1 Motivation and Definition 2 Universal Approximation 3 Backpropagation 4 Stochastic Gradient

More information