An Introduction to Deep Learning with RapidMiner. Philipp Schlunder - RapidMiner Research
|
|
|
- Arleen Avis Blake
- 6 years ago
- Views:
Transcription
1 An Introduction to Deep Learning with RapidMiner Philipp Schlunder - RapidMiner Research
2 What s in store for today?. Things to know before getting started 2. What s Deep Learning anyway? 3. How to use it inside RapidMiner 207 RapidMiner, Inc. All rights reserved
3 Before getting up to speed 207 RapidMiner, Inc. All rights reserved
4 What do I actually need? Hardware Minimum Recommended Starter Kit Optimum PC or Mac running RapidMiner Software PC with supported NVIDIA GPU running Linux/Windows Dedicated Server with multiple GPUs running Linux RapidMiner Studio or RapidMiner Server Python installation (at least Version 3.5) with Pandas Linux recommended: Tensorflow (for GPUs) Windows recommended: Microsoft CNTK Keras extension Tensorflow Keras Cognitive Toolkit Theano 207 RapidMiner, Inc. All rights reserved. - -
5 I don t have a server with GPUs! We ve got you covered with RapidMiner Server on the Amazon AWS and Microsoft Azure marketplaces Put your server where your data is Server installation in minutes No need for own hardware Bring-your-own-license images (Amazon AMIs & Microsoft VHDs) 207 RapidMiner, Inc. All rights reserved
6 When should I try Deep Learning?. Stuck with current model Accuracy not high enough 2. Huge amount of training data available 3. Fixed specific use-case. Need notion of memory Understanding context 5. Multi-dimensional input Pictures: 3 colors per Pixel Text: Word Vectors 207 RapidMiner, Inc. All rights reserved
7 Things to consider Large number of parameters to tune often req. huge amount of data Is my infrastructure suited for that? Is the potential ROI high enough for the resource investment? For many general ML tasks only minor improvement Often not that flexible and very domain specific Hard to understand reasoning (consider LIME) General Data Protection Regulation (25 th of May 208, EU-based) right to an explanation prevent discriminatory effects based on race, opinions, health 207 RapidMiner, Inc. All rights reserved
8 What is Deep Learning anyway? 207 RapidMiner, Inc. All rights reserved
9 Machine Learning 207 RapidMiner, Inc. All rights reserved
10 Hierarchical Learning 207 RapidMiner, Inc. All rights reserved
11 Hierarchical Learning Input First Representation Second Representation 207 RapidMiner, Inc. All rights reserved. - -
12 Hierarchical Learning 207 RapidMiner, Inc. All rights reserved
13 Deep Learning 3x 207 RapidMiner, Inc. All rights reserved
14 Layers Input Layer Hidden Layer Output Layer 207 RapidMiner, Inc. All rights reserved. - -
15 Neurons Input Layer Number of Attributes Hidden Layer Output Layer 207 RapidMiner, Inc. All rights reserved
16 Neurons Input Layer Number of Attributes Hidden Layer Output Layer Number of Label values 207 RapidMiner, Inc. All rights reserved
17 Neurons Input Layer Number of Attributes Hidden Layer Output Layer Number of Label values New Attribute based on previous ones and some activation function (e.g. ReLu) 207 RapidMiner, Inc. All rights reserved
18 Layer: Fully-Connected Input Layer Hidden Layer Output Layer Fully-Connected (Dense) Layer 207 RapidMiner, Inc. All rights reserved
19 Change of Perspective 207 RapidMiner, Inc. All rights reserved
20 Layer: Convolutional 207 RapidMiner, Inc. All rights reserved
21 Layer: Convolutional 207 RapidMiner, Inc. All rights reserved
22 Layer: Convolutional Activation Map Example Filter X = N = F = 2 (N F) / Stride RapidMiner, Inc. All rights reserved
23 Layer: Convolutional Activation Map Example Filter X = N = F = 2 (N F) / Stride RapidMiner, Inc. All rights reserved
24 Layer: Convolutional Activation Map Example Filter Stride = X = N = F = 2 (N F) / Stride + = ( 2) / + = RapidMiner, Inc. All rights reserved
25 Layer: Convolutional Activation Map Example Filter X = x + 3x0 + x0 + 7x = 207 RapidMiner, Inc. All rights reserved
26 Layer: Convolutional Activation Map Example Filter X = RapidMiner, Inc. All rights reserved
27 Layer: Convolutional Activation Map Example Filter X = RapidMiner, Inc. All rights reserved
28 Layer: Convolutional Activation Map Example Filter X = RapidMiner, Inc. All rights reserved
29 Layer: Convolutional Activation Map Example Filter X = RapidMiner, Inc. All rights reserved
30 Layer: Convolutional Padding = RapidMiner, Inc. All rights reserved
31 Layer: Convolutional Activation Map 207 RapidMiner, Inc. All rights reserved
32 Layer: Convolutional Filter: Activation Map RapidMiner, Inc. All rights reserved
33 Layer: Convolutional Filter: Activation Map Convolutional Layer 207 RapidMiner, Inc. All rights reserved
34 Layer: Pooling Max(imum) Pooling RapidMiner, Inc. All rights reserved
35 Layer: Pooling Stride = Max(imum) Pooling RapidMiner, Inc. All rights reserved
36 Layer: Pooling Max(imum) Pooling RapidMiner, Inc. All rights reserved
37 Layer: Pooling Max(imum) Pooling RapidMiner, Inc. All rights reserved
38 Layer: Pooling Max(imum) Pooling Average Pooling / 2 / 22 / 9 / 207 RapidMiner, Inc. All rights reserved
39 Layer: Pooling Max(imum) Pooling Representation becomes smaller less values to optimize Applied to each activation map of the previous layer 207 RapidMiner, Inc. All rights reserved
40 Layer: Recurrent State of the layer s 0 s RapidMiner, Inc. All rights reserved
41 Layer: Recurrent s s State of the layer changes with each repetition 207 RapidMiner, Inc. All rights reserved. - -
42 Layer: Recurrent s 3 I drank some coffee s s 2 s 0 Drinking a hot beverage that [ ] for me it is coffee. s 0 s s 2 s 93 Neurons with hidden states 207 RapidMiner, Inc. All rights reserved
43 Layer: Long Short Term Memory Information can be: Not stored (input) Only stored s prev partially (gate) Forgotten Be considered only i g f o partially (output) 207 RapidMiner, Inc. All rights reserved
44 Layer: Dropout Dropout is a form of regularization. It helps reduce complexity and frame the model. Dropout Rate Probability of dropping a neuron Between 0 and 207 RapidMiner, Inc. All rights reserved. - -
45 Input & Setup 207 RapidMiner, Inc. All rights reserved
46 Input Input Layer Hidden Layer Output Layer 207 RapidMiner, Inc. All rights reserved
47 Input Input Layer input_shape depends on layers used Convolution/Recurrent: (timesteps, input_dim) = (, 3) Others: (input_dim,) = (3,) 207 RapidMiner, Inc. All rights reserved
48 Input Input Layer input_shape Convolution/Recurrent: (timesteps, input_dim) = (,3) since the data contains timesteps 207 RapidMiner, Inc. All rights reserved
49 Input Input Data Set Entry (picture, sentence, ) batch_size Number of entries to use in one model building step (obtaining weights) Here: Batch 207 RapidMiner, Inc. All rights reserved
50 The Model Weights Weight amount of a neuron s contribution Weights are changed using an optimizer An optimizer reduces the loss One weight change cycle is called an epoch weights 207 RapidMiner, Inc. All rights reserved
51 The Model Building it Parameter Binary Classification Multi-Class Classification Regression optimizer adam/rmsprop adam/rmsprop adam/rmsprop loss binary_crossentropy categorical_crossentropy mse While training observe loss (log/tensorboard): Bump change weight init Lowers slowly learning rate too low Fast decline, then stagnating learning rate too high Brief decline, rises extremely afterwards learning rate way too high rmsprop: esp. good choice for recurrent adam: rmsprop with extra (momentum) 207 RapidMiner, Inc. All rights reserved
52 input convolution convolution pooling convolution convolution pooling recurrent fully-connected output The Model Architecture Start small and simple Test overfitting on small batch (small loss, ~.0 accuracy) Add regularization until loss goes down Not going down, learning rate too low Constant or NaN, learning rate too high Hyper Parameter Tuning Often: No. filters rises ( ) Filter size shrinks (5 3) Stride shrinks (2 ) Padding is introduced (0 ) 207 RapidMiner, Inc. All rights reserved
53 Deep Learning Summary 207 RapidMiner, Inc. All rights reserved
54 Summary Different Types of Layers: Fully-connected, convolutional, recurrent, pooling, dropout, Model is defined by: Setup of layers (architecture) Weights obtained through optimization of a loss over several epochs Classification vs. Regression: Change number of units in last layer (Number of possible classes vs. number of targeted values to predict) Change loss from crossentropy to mse 207 RapidMiner, Inc. All rights reserved
55 How to use it in RapidMiner? 207 RapidMiner, Inc. All rights reserved
56 Options in RapidMiner Feature Neural Net Deep Learning H20 Deep Learning Keras Fully-Connected Layer X X X Basic Optimization X X X Advanced Optimization X X Multi-Threading X X GPU Support Advanced Layers Complexity X X 207 RapidMiner, Inc. All rights reserved
57 Demo Time 207 RapidMiner, Inc. All rights reserved
58 Classification 207 RapidMiner, Inc. All rights reserved
59 Classification 207 RapidMiner, Inc. All rights reserved
60 Classification 207 RapidMiner, Inc. All rights reserved
61 Classification 3 label values 207 RapidMiner, Inc. All rights reserved
62 Regression 207 RapidMiner, Inc. All rights reserved
63 Regression 207 RapidMiner, Inc. All rights reserved
64 Regression 207 RapidMiner, Inc. All rights reserved
65 Regression 32 entries 256 iterations of changing/optimizing the weights with a method called Adam 207 RapidMiner, Inc. All rights reserved
66 Regression 207 RapidMiner, Inc. All rights reserved
67 Regression 6 filters 6 activation maps 207 RapidMiner, Inc. All rights reserved
68 Regression RapidMiner, Inc. All rights reserved
69 Regression 207 RapidMiner, Inc. All rights reserved
70 Regression 207 RapidMiner, Inc. All rights reserved
71 Regression 250 neurons 207 RapidMiner, Inc. All rights reserved
72 Regression value to estimate (closing date of 30th timestep) 207 RapidMiner, Inc. All rights reserved
73 Regression Log storage directory 207 RapidMiner, Inc. All rights reserved
74 Regression Start Tensorboard with log storage directory location provided through command line Log storage directory tensorboard --logdir=c:/users/philippschlunder/desktop/logs/ View loss graph in Browser under the address: Localhost: RapidMiner, Inc. All rights reserved
75 Philipp Q & A Download RapidMiner 7.6 inquiries@rapidminer.com 207 RapidMiner, Inc. All rights reserved
76 Sources Stanford CS23n Keras docu When not to use deep learning Deep Learning is not the AI future 207 RapidMiner, Inc. All rights reserved
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
A Quick Guide on Training a neural network using Keras.
A Quick Guide on Training a neural network using Keras. TensorFlow and Keras Keras Open source High level, less flexible Easy to learn Perfect for quick implementations Starts by François Chollet from
Deep Nets with. Keras
docs https://keras.io Deep Nets with Keras κέρας http://vem.quantumunlimited.org/the-gates-of-horn/ Professor Marie Roch These slides only cover enough to get started with feed-forward networks and do
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
Index. Umberto Michelucci 2018 U. Michelucci, Applied Deep Learning,
A Acquisition function, 298, 301 Adam optimizer, 175 178 Anaconda navigator conda command, 3 Create button, 5 download and install, 1 installing packages, 8 Jupyter Notebook, 11 13 left navigation pane,
Keras: Handwritten Digit Recognition using MNIST Dataset
Keras: Handwritten Digit Recognition using MNIST Dataset IIT PATNA February 9, 2017 1 / 24 OUTLINE 1 Introduction Keras: Deep Learning library for Theano and TensorFlow 2 Installing Keras Installation
Code Mania Artificial Intelligence: a. Module - 1: Introduction to Artificial intelligence and Python:
Code Mania 2019 Artificial Intelligence: a. Module - 1: Introduction to Artificial intelligence and Python: 1. Introduction to Artificial Intelligence 2. Introduction to python programming and Environment
Deep Learning Frameworks. COSC 7336: Advanced Natural Language Processing Fall 2017
Deep Learning Frameworks COSC 7336: Advanced Natural Language Processing Fall 2017 Today s lecture Deep learning software overview TensorFlow Keras Practical Graphical Processing Unit (GPU) From graphical
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
Deep Learning. Practical introduction with Keras JORDI TORRES 27/05/2018. Chapter 3 JORDI TORRES
Deep Learning Practical introduction with Keras Chapter 3 27/05/2018 Neuron A neural network is formed by neurons connected to each other; in turn, each connection of one neural network is associated
An Introduction to NNs using Keras
An Introduction to NNs using Keras Michela Paganini michela.paganini@cern.ch Yale University 1 Keras Modular, powerful and intuitive Deep Learning python library built on Theano and TensorFlow Minimalist,
Lecture 20: Neural Networks for NLP. Zubin Pahuja
Lecture 20: Neural Networks for NLP Zubin Pahuja zpahuja2@illinois.edu courses.engr.illinois.edu/cs447 CS447: Natural Language Processing 1 Today s Lecture Feed-forward neural networks as classifiers simple
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
Machine Learning and Algorithms for Data Mining Practical 2: Neural Networks
CST Part III/MPhil in Advanced Computer Science 2016-2017 Machine Learning and Algorithms for Data Mining Practical 2: Neural Networks Demonstrators: Petar Veličković, Duo Wang Lecturers: Mateja Jamnik,
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
ECE 5470 Classification, Machine Learning, and Neural Network Review
ECE 5470 Classification, Machine Learning, and Neural Network Review Due December 1. Solution set Instructions: These questions are to be answered on this document which should be submitted to blackboard
Why data science is the new frontier in software development
Why data science is the new frontier in software development And why every developer should care Jeff Prosise jeffpro@wintellect.com @jprosise Assertion #1 Being a programmer is like being the god of your
Deep Learning Basic Lecture - Complex Systems & Artificial Intelligence 2017/18 (VO) Asan Agibetov, PhD.
Deep Learning 861.061 Basic Lecture - Complex Systems & Artificial Intelligence 2017/18 (VO) Asan Agibetov, PhD asan.agibetov@meduniwien.ac.at Medical University of Vienna Center for Medical Statistics,
Encoding RNNs, 48 End of sentence (EOS) token, 207 Exploding gradient, 131 Exponential function, 42 Exponential Linear Unit (ELU), 44
A Activation potential, 40 Annotated corpus add padding, 162 check versions, 158 create checkpoints, 164, 166 create input, 160 create train and validation datasets, 163 dropout, 163 DRUG-AE.rel file,
ImageNet Classification with Deep Convolutional Neural Networks
ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky Ilya Sutskever Geoffrey Hinton University of Toronto Canada Paper with same name to appear in NIPS 2012 Main idea Architecture
The Mathematics Behind Neural Networks
The Mathematics Behind Neural Networks Pattern Recognition and Machine Learning by Christopher M. Bishop Student: Shivam Agrawal Mentor: Nathaniel Monson Courtesy of xkcd.com The Black Box Training the
Review: The best frameworks for machine learning and deep learning
Review: The best frameworks for machine learning and deep learning infoworld.com/article/3163525/analytics/review-the-best-frameworks-for-machine-learning-and-deep-learning.html By Martin Heller Over the
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
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
Machine Learning With Python. Bin Chen Nov. 7, 2017 Research Computing Center
Machine Learning With Python Bin Chen Nov. 7, 2017 Research Computing Center Outline Introduction to Machine Learning (ML) Introduction to Neural Network (NN) Introduction to Deep Learning NN Introduction
Perceptron: This is convolution!
Perceptron: This is convolution! v v v Shared weights v Filter = local perceptron. Also called kernel. By pooling responses at different locations, we gain robustness to the exact spatial location of image
CIS581: Computer Vision and Computational Photography Project 4, Part B: Convolutional Neural Networks (CNNs) Due: Dec.11, 2017 at 11:59 pm
CIS581: Computer Vision and Computational Photography Project 4, Part B: Convolutional Neural Networks (CNNs) Due: Dec.11, 2017 at 11:59 pm Instructions CNNs is a team project. The maximum size of a team
Advanced Video Analysis & Imaging
Advanced Video Analysis & Imaging (5LSH0), Module 09B Machine Learning with Convolutional Neural Networks (CNNs) - Workout Farhad G. Zanjani, Clint Sebastian, Egor Bondarev, Peter H.N. de With ( p.h.n.de.with@tue.nl
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
Sentiment Classification of Food Reviews
Sentiment Classification of Food Reviews Hua Feng Department of Electrical Engineering Stanford University Stanford, CA 94305 fengh15@stanford.edu Ruixi Lin Department of Electrical Engineering Stanford
CS489/698: Intro to ML
CS489/698: Intro to ML Lecture 14: Training of Deep NNs Instructor: Sun Sun 1 Outline Activation functions Regularization Gradient-based optimization 2 Examples of activation functions 3 5/28/18 Sun Sun
Neural networks. About. Linear function approximation. Spyros Samothrakis Research Fellow, IADS University of Essex.
Neural networks Spyros Samothrakis Research Fellow, IADS University of Essex About Linear function approximation with SGD From linear regression to neural networks Practical aspects February 28, 2017 Conclusion
Vinnie Saini Cloud Solution Architect Big Data & AI
Vinnie Saini Cloud Solution Architect Big Data & AI vasaini@microsoft.com data intelligence cloud Data + Intelligence + Cloud Extensible Applications Easy to consume Artificial Intelligence Most comprehensive
NVIDIA FOR DEEP LEARNING. Bill Veenhuis
NVIDIA FOR DEEP LEARNING Bill Veenhuis bveenhuis@nvidia.com Nvidia is the world s leading ai platform ONE ARCHITECTURE CUDA 2 GPU: Perfect Companion for Accelerating Apps & A.I. CPU GPU 3 Intro to AI AGENDA
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
Deep Learning Applications
October 20, 2017 Overview Supervised Learning Feedforward neural network Convolution neural network Recurrent neural network Recursive neural network (Recursive neural tensor network) Unsupervised Learning
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
Natural Language Processing CS 6320 Lecture 6 Neural Language Models. Instructor: Sanda Harabagiu
Natural Language Processing CS 6320 Lecture 6 Neural Language Models Instructor: Sanda Harabagiu In this lecture We shall cover: Deep Neural Models for Natural Language Processing Introduce Feed Forward
Frameworks in Python for Numeric Computation / ML
Frameworks in Python for Numeric Computation / ML Why use a framework? Why not use the built-in data structures? Why not write our own matrix multiplication function? Frameworks are needed not only because
A Deep Learning Approach to Vehicle Speed Estimation
A Deep Learning Approach to Vehicle Speed Estimation Benjamin Penchas bpenchas@stanford.edu Tobin Bell tbell@stanford.edu Marco Monteiro marcorm@stanford.edu ABSTRACT Given car dashboard video footage,
Deep Learning on AWS with TensorFlow and Apache MXNet
Deep Learning on AWS with TensorFlow and Apache MXNet Julien Simon Global Evangelist, AI & Machine Learning @julsimon Renaud ALLIOUX CTO, Earthcube The Amazon ML Stack: Broadest & Deepest Set of Capabilities
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)
Practical Methodology. Lecture slides for Chapter 11 of Deep Learning Ian Goodfellow
Practical Methodology Lecture slides for Chapter 11 of Deep Learning www.deeplearningbook.org Ian Goodfellow 2016-09-26 What drives success in ML? Arcane knowledge of dozens of obscure algorithms? Mountains
Deep Learning. Vladimir Golkov Technical University of Munich Computer Vision Group
Deep Learning Vladimir Golkov Technical University of Munich Computer Vision Group 1D Input, 1D Output target input 2 2D Input, 1D Output: Data Distribution Complexity Imagine many dimensions (data occupies
Machine Learning. MGS Lecture 3: Deep Learning
Dr Michel F. Valstar http://cs.nott.ac.uk/~mfv/ Machine Learning MGS Lecture 3: Deep Learning Dr Michel F. Valstar http://cs.nott.ac.uk/~mfv/ WHAT IS DEEP LEARNING? Shallow network: Only one hidden layer
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
Deep Learning in NLP. Horacio Rodríguez. AHLT Deep Learning 2 1
Deep Learning in NLP Horacio Rodríguez AHLT Deep Learning 2 1 Outline Introduction Short review of Distributional Semantics, Semantic spaces, VSM, Embeddings Embedding of words Embedding of more complex
Machine Learning in WAN Research
Machine Learning in WAN Research Mariam Kiran mkiran@es.net Energy Sciences Network (ESnet) Lawrence Berkeley National Lab Oct 2017 Presented at Internet2 TechEx 2017 Outline ML in general ML in network
Package kerasr. June 1, 2017
Type Package Package kerasr June 1, 2017 Title R Interface to the Keras Deep Learning Library Version 0.6.1 Author Taylor Arnold [aut, cre] Maintainer Taylor Arnold Provides a consistent
Software and Practical Methodology. Tambet Matiisen Neural Networks course
Software and Practical Methodology Tambet Matiisen Neural Networks course 30.10.2017 Deep Learning Software Use web API Use pre-trained model Fine-tune pre-trained model Train your own model Write custom
Deep Neural Networks Optimization
Deep Neural Networks Optimization Creative Commons (cc) by Akritasa http://arxiv.org/pdf/1406.2572.pdf Slides from Geoffrey Hinton CSC411/2515: Machine Learning and Data Mining, Winter 2018 Michael Guerzhoy
Deep Neural Network Hyperparameter Optimization with Genetic Algorithms
Deep Neural Network Hyperparameter Optimization with Genetic Algorithms EvoDevo A Genetic Algorithm Framework Aaron Vose, Jacob Balma, Geert Wenes, and Rangan Sukumar Cray Inc. October 2017 Presenter Vose,
Application of Deep Learning Techniques in Satellite Telemetry Analysis.
Application of Deep Learning Techniques in Satellite Telemetry Analysis. Greg Adamski, Member of Technical Staff L3 Technologies Telemetry and RF Products Julian Spencer Jones, Spacecraft Engineer Telenor
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
GPU Based Image Classification using Convolutional Neural Network Chicken Dishes Classification
Int. J. Advance Soft Compu. Appl, Vol. 10, No. 2, July 2018 ISSN 2074-8523 GPU Based Image Classification using Convolutional Neural Network Chicken Dishes Classification Hafizhan Aliady, Dina Tri Utari
Accelerating Convolutional Neural Nets. Yunming Zhang
Accelerating Convolutional Neural Nets Yunming Zhang Focus Convolutional Neural Nets is the state of the art in classifying the images The models take days to train Difficult for the programmers to tune
Real-Time Depth Estimation from 2D Images
Real-Time Depth Estimation from 2D Images Jack Zhu Ralph Ma jackzhu@stanford.edu ralphma@stanford.edu. Abstract ages. We explore the differences in training on an untrained network, and on a network pre-trained
DEEP LEARNING IN PYTHON. Introduction to deep learning
DEEP LEARNING IN PYTHON Introduction to deep learning Imagine you work for a bank You need to predict how many transactions each customer will make next year Example as seen by linear regression Age Bank
Day 1 Lecture 6. Software Frameworks for Deep Learning
Day 1 Lecture 6 Software Frameworks for Deep Learning Packages Caffe Theano NVIDIA Digits Lasagne Keras Blocks Torch TensorFlow MxNet MatConvNet Nervana Neon Leaf Caffe Deep learning framework from Berkeley
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
Shrinath Shanbhag Senior Software Engineer Microsoft Corporation
Accelerating GPU inferencing with DirectML and DirectX 12 Shrinath Shanbhag Senior Software Engineer Microsoft Corporation Machine Learning Machine learning has become immensely popular over the last decade
End-to-end Driving Controls Predictions from Images
End-to-end Driving Controls Predictions from Images Jan Felix Heyse and Maxime Bouton CS229 Final Project Report December 17, 2016 Abstract Autonomous driving is a promising technology to improve transportation
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-
Kaggle Data Science Bowl 2017 Technical Report
Kaggle Data Science Bowl 2017 Technical Report qfpxfd Team May 11, 2017 1 Team Members Table 1: Team members Name E-Mail University Jia Ding dingjia@pku.edu.cn Peking University, Beijing, China Aoxue Li
Machine Learning in WAN Research
Machine Learning in WAN Research Mariam Kiran mkiran@es.net Energy Sciences Network (ESnet) Lawrence Berkeley National Lab Oct 2017 Presented at Internet2 TechEx 2017 Outline ML in general ML in network
CS 6501: Deep Learning for Computer Graphics. Training Neural Networks II. Connelly Barnes
CS 6501: Deep Learning for Computer Graphics Training Neural Networks II Connelly Barnes Overview Preprocessing Initialization Vanishing/exploding gradients problem Batch normalization Dropout Additional
Deep Learning for Developers
Deep Learning for Developers Julien Simon Principal Evangelist, AI/ML, EMEA 2017, Amazon Web Services, Inc. or its affiliates. All rights reserved Questions, questions What s the seemingly
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
Deep Learning with R. Francesca Lazzeri Data Scientist II - Microsoft, AI Research
with R Francesca Lazzeri - @frlazzeri Data Scientist II - Microsoft, AI Research Agenda with R What is Demo Better understanding of R DL tools Fundamental concepts in Forward Propagation Algorithm Activation
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
Fig 2.1 Typical prediction results by linear regression with HOG
Facial Keypoints Detection Hao Zhang Jia Chen Nitin Agarwal (hzhang10, 61526092) (jiac5, 35724702) (agarwal,84246130) 1. Introduction The objective of the project is to detect the location of keypoints
Managing Deep Learning Workflows
Managing Deep Learning Workflows Deep Learning on AWS Batch treske@amazon.de September 2017 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Business Understanding Data Understanding
Analyzing rtweet data with kerasformula
Analyzing rtweet data with kerasformula Pete Mohanty BARUG March 2018 hosted by Google Overview Now on CRAN, kerasformula package offers a high-level interface for the R interface to Keras. install.packages("kerasformula")
CPSC 340: Machine Learning and Data Mining. Deep Learning Fall 2016
CPSC 340: Machine Learning and Data Mining Deep Learning Fall 2016 Assignment 5: Due Friday. Assignment 6: Due next Friday. Final: Admin December 12 (8:30am HEBB 100) Covers Assignments 1-6. Final from
NVIDIA GPU CLOUD DEEP LEARNING FRAMEWORKS
TECHNICAL OVERVIEW NVIDIA GPU CLOUD DEEP LEARNING FRAMEWORKS A Guide to the Optimized Framework Containers on NVIDIA GPU Cloud Introduction Artificial intelligence is helping to solve some of the most
Characterization and Benchmarking of Deep Learning. Natalia Vassilieva, PhD Sr. Research Manager
Characterization and Benchmarking of Deep Learning Natalia Vassilieva, PhD Sr. Research Manager Deep learning applications Vision Speech Text Other Search & information extraction Security/Video surveillance
CSC 578 Neural Networks and Deep Learning
CSC 578 Neural Networks and Deep Learning Fall 2018/19 7. Recurrent Neural Networks (Some figures adapted from NNDL book) 1 Recurrent Neural Networks 1. Recurrent Neural Networks (RNNs) 2. RNN Training
BAYESIAN GLOBAL OPTIMIZATION
BAYESIAN GLOBAL OPTIMIZATION Using Optimal Learning to Tune Deep Learning Pipelines Scott Clark scott@sigopt.com OUTLINE 1. Why is Tuning AI Models Hard? 2. Comparison of Tuning Methods 3. Bayesian Global
Mask R-CNN. By Kaiming He, Georgia Gkioxari, Piotr Dollar and Ross Girshick Presented By Aditya Sanghi
Mask R-CNN By Kaiming He, Georgia Gkioxari, Piotr Dollar and Ross Girshick Presented By Aditya Sanghi Types of Computer Vision Tasks http://cs231n.stanford.edu/ Semantic vs Instance Segmentation Image
Deep Learning Frameworks with Spark and GPUs
Deep Learning Frameworks with Spark and GPUs Abstract Spark is a powerful, scalable, real-time data analytics engine that is fast becoming the de facto hub for data science and big data. However, in parallel,
Restricted Boltzmann Machines. Shallow vs. deep networks. Stacked RBMs. Boltzmann Machine learning: Unsupervised version
Shallow vs. deep networks Restricted Boltzmann Machines Shallow: one hidden layer Features can be learned more-or-less independently Arbitrary function approximator (with enough hidden units) Deep: two
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
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
Neural Network Optimization and Tuning / Spring 2018 / Recitation 3
Neural Network Optimization and Tuning 11-785 / Spring 2018 / Recitation 3 1 Logistics You will work through a Jupyter notebook that contains sample and starter code with explanations and comments throughout.
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
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
Convolution Neural Network for Traditional Chinese Calligraphy Recognition
Convolution Neural Network for Traditional Chinese Calligraphy Recognition Boqi Li Mechanical Engineering Stanford University boqili@stanford.edu Abstract script. Fig. 1 shows examples of the same TCC
M. Sc. (Artificial Intelligence and Machine Learning)
Course Name: Advanced Python Course Code: MSCAI 122 This course will introduce students to advanced python implementations and the latest Machine Learning and Deep learning libraries, Scikit-Learn and
Deep Learning for Embedded Security Evaluation
Deep Learning for Embedded Security Evaluation Emmanuel Prouff 1 1 Laboratoire de Sécurité des Composants, ANSSI, France April 2018, CISCO April 2018, CISCO E. Prouff 1/22 Contents 1. Context and Motivation
MACHINE LEARNING CLASSIFIERS ADVANTAGES AND CHALLENGES OF SELECTED METHODS
MACHINE LEARNING CLASSIFIERS ADVANTAGES AND CHALLENGES OF SELECTED METHODS FRANK ORBEN, TECHNICAL SUPPORT / DEVELOPER IMAGE PROCESSING, STEMMER IMAGING OUTLINE Introduction Task: Classification Theory
Xilinx ML Suite Overview
Xilinx ML Suite Overview Yao Fu System Architect Data Center Acceleration Xilinx Accelerated Computing Workloads Machine Learning Inference Image classification and object detection Video Streaming Frame
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
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
Multi-Glance Attention Models For Image Classification
Multi-Glance Attention Models For Image Classification Chinmay Duvedi Stanford University Stanford, CA cduvedi@stanford.edu Pararth Shah Stanford University Stanford, CA pararth@stanford.edu Abstract We
Practical Deep Learning
Practical Deep Learning micha.codes / fastforwardlabs.com 1 / 70 deep learning can seem mysterious 2 / 70 let's nd a way to just build a function 3 / 70 Feed Forward Layer # X.shape == (512,) # output.shape
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:
Event: PASS SQL Saturday - DC 2018 Presenter: Jon Tupitza, CTO Architect
Event: PASS SQL Saturday - DC 2018 Presenter: Jon Tupitza, CTO Architect BEOP.CTO.TP4 Owner: OCTO Revision: 0001 Approved by: JAT Effective: 08/30/2018 Buchanan & Edwards Proprietary: Printed copies of
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
Deep Learning for Visual Computing Prof. Debdoot Sheet Department of Electrical Engineering Indian Institute of Technology, Kharagpur
Deep Learning for Visual Computing Prof. Debdoot Sheet Department of Electrical Engineering Indian Institute of Technology, Kharagpur Lecture - 05 Classification with Perceptron Model So, welcome to today
DEEP LEARNING IN PYTHON. Creating a keras model
DEEP LEARNING IN PYTHON Creating a keras model Model building steps Specify Architecture Compile Fit Predict Model specification In [1]: import numpy as np In [2]: from keras.layers import Dense In [3]: