Deep Learning Explained Module 6: Text classification with Recurrence (LSTM)
|
|
|
- Jodie Gibbs
- 6 years ago
- Views:
Transcription
1 eep earning xplained Module 6: Text classification with Recurrence (STM) Sayan. Pathak, Ph.., Principal M Scientist, Microsoft Roland Fernandez, Senior Researcher, Microsoft
2 Module outline Application: Text classification with ATIS data Model: Recurrence ong-short term memory cell ifferent recurrent networks Concept: mbedding Train-Test-Predict Workflow
3 Sequences (many to many) Problem: Tagging entities in Air Traffic Controller (ATIS) data Class label o From_city o To_city o ate Rec Rec Rec Rec Rec Rec Rec Text token show burbank to seattle flights tomorrow
4 ATIS data omain: ATIS contains human-computer queries from the domain of Air Travel Information Services. ata summary: 943 unique words a.k.a. : Vocabulary 129 unique tags a.k.a.: abels 26 intent tags: not used in this tutorial
5 Sequence Id Input Word (sample) Word Index (in vocabulary) S0 Word abel abel Index (S2) 19 # BOS 178:1 # O 128:1 19 # please 688:1 # O 128:1 19 # give 449:1 # O 128:1 19 # me 581:1 # O 128:1 19 # the 827:1 # O 128:1 19 # flights 429:1 # O 128:1 19 # from 444:1 # O 128:1 19 # boston 266:1 # B-fromloc.city_name 48:1 19 # to 851:1 # O 128:1 19 # pittsburgh 682:1 # B-toloc.city_name 78:1 19 # on 654:1 # O 128:1 19 # thursday 845:1 # B-depart_date.day_name 26:1 19 # of 646:1 # O 128:1 19 # next 621:1 # B-depart_date.date_relative 25:1 19 # week 910:1 # O 128:1 19 # OS 179:1 # O 128:1 Sequence Id: Word Index: abel Index: 19 indicates this sentence is the 19 th sentence in the data set ###:1 indicates the position of the corresponding word in the vocabulary (total 943 words) ###:1 indicates the position of the corresponding tag in tag index (total 129 tags)
6 Sequence Tagging (Input / abel Pre-processing) Create a numerical representation of the input words For MNIST data: abel One-hot encoded (Y) For each word - One-hot representation is a vector with 943 elements 266 th element 943 th element For each label one-hot representation is a vector with 129 elements
7 mbedding Class label One-hot ncoding Numerical representation of text Word mbedding Technique to map words or phrases to vector of real numbers. Maps one-hot encoded vector to a lower dimensional space Rec inear mbedding Multiply a matrix with one-hot encoded vector (W e X T ) X T : vector of size 1 x 943 W e : matrix of size 150 x 943 Popular mbedding GloVe ( Word2Vec ( 1 x 150 X T x 943 Text token
8 Model Ԧy(t) Class label Ԧy(t) ense i = 300 O= 129 a = sigmoid STM Recurrence h(t-1) i = 150 O= 300 h(t) mbedding i = 943 O= 150 Ԧx(t) Text token Ԧx(t)
9 Text classification Problem: Tagging entities in Air Traffic Controller (ATIS) data #O #O B-fromloc. City_name #O B-toloc. City_name #O B-depart_date. day_name #O B-depart_date. ay_relative #O # BOS # O # from # O # boston # B-fromloc.city_name # to # O # pittsburgh # B-toloc.city_name # on # O # thursday # B-depart_date.day_name # of # O # next # B-depart_date.date_relative # week # O # OS # O #O BOS from boston to pittsburgh on thursday of next week week
10 Text classification Problem: Tagging entities in Air Traffic Controller (ATIS) data # BOS # O # from # O # boston # B-fromloc.city_name # to # O # pittsburgh # B-toloc.city_name # on # O # thursday # B-depart_date.day_name # of # O # next # B-depart_date.date_relative # week # O # OS # O Class label Ԧy(t) ense STM Recurrence mbedding 'BOS from boston to Pittsburgh on Thursday of next week OS' Input feature (1 x 11 x (1x943)) #1 Text token Ԧx(t)
11 rror or oss Function abel One-hot encoded ( Ԧy(t)) Ԧx(t) oss function 9 ce = σ j=0 y j log p j Cross entropy error Model Predicted Probabilities (p) 129
12 Train / Validation Workflow
13 96 samples (mini-batch).... Train Workflow Input feature ( 96 x Ԧx(t)) #1 t 1 #2 t 1 t 15 #3 t 1 t 9 #96 t 1 t 12 t 23 z = model(): return Sequential([ mbedding(emb_dim=150), Recurrence(STM(hidden_dim=300), go_backwards=false), ense(num_labels = 129) ]) ATIS Train One-hot encoded abel (Y: 96 x 129/sample Or word in sequence) oss rror cross_entropy_with_softmax(z,y) classification_error(z,y) Trainer(model, (loss, error), learner) Trainer.train_minibatch({X, Y}) earner Adam, adagrad etc, are solvers to estimate
14 Test workflow Test ata ata Sampler Features (x), abels (Y) Model final trained params Test Reporting Test more? Y
15 32 samples (mini-batch).... Test workflow Input feature ( 32 x Ԧx(t)) 1 2 t 1 t 1 t 12 3 t 1 t 7 32 t 1 t 10 t 20 z = model(): return Sequential([ mbedding(emb_dim=150), Recurrence(STM(hidden_dim=300), go_backwards=false), ense(num_labels = 129) ]) ATIS Test One-hot encoded abel (Y: 32 x 129/sample Or word in sequence) Trainer.test_minibatch({X, Y}) Returns the classification error as % incorrectly labeled tokens.
16 Prediction workflow Any ata string 'BOS flights from new york to seattle OS' Input feature (new X: 1 x 8 x (1x943)) t 1 t 9 Model.eval(new X) Predicted Softmax Probabilities Output prediction (1 x 8 x (1x129))
17 Sequences (many to many) hallo wie geht es dir </s> Rec Rec Rec Rec Rec Rec Rec Rec Rec Rec hello how are you <s>
18 Sequences (one to many) a person a kite Rec Rec Rec Rec Vinyals et al (
19 Conclusion eep learning concepts - oss functions, Mini-batch - Activation functions - Convolution, Pooling - Recurrence, STM, ropout, mbeddings eep neural networks models - Multi-class logistic regression - Multi-layered perceptron - Convolutional neural networks - Recurrent networks with STM - Recurrent networks with STM and word embeddings Train-Test-Predict using NN models
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
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
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
Tutorial on Machine Learning Tools
Tutorial on Machine Learning Tools Yanbing Xue Milos Hauskrecht Why do we need these tools? Widely deployed classical models No need to code from scratch Easy-to-use GUI Outline Matlab Apps Weka 3 UI TensorFlow
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
Machine Learning: Chenhao Tan University of Colorado Boulder LECTURE 15
Machine Learning: Chenhao Tan University of Colorado Boulder LECTURE 15 Slides adapted from Jordan Boyd-Graber Machine Learning: Chenhao Tan Boulder 1 of 21 Logistics HW3 available on Github, due on October
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
Recurrent Neural Nets II
Recurrent Neural Nets II Steven Spielberg Pon Kumar, Tingke (Kevin) Shen Machine Learning Reading Group, Fall 2016 9 November, 2016 Outline 1 Introduction 2 Problem Formulations with RNNs 3 LSTM for Optimization
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
Lecture 2 Notes. Outline. Neural Networks. The Big Idea. Architecture. Instructors: Parth Shah, Riju Pahwa
Instructors: Parth Shah, Riju Pahwa Lecture 2 Notes Outline 1. Neural Networks The Big Idea Architecture SGD and Backpropagation 2. Convolutional Neural Networks Intuition Architecture 3. Recurrent Neural
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
Layerwise Interweaving Convolutional LSTM
Layerwise Interweaving Convolutional LSTM Tiehang Duan and Sargur N. Srihari Department of Computer Science and Engineering The State University of New York at Buffalo Buffalo, NY 14260, United States
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,
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
Deep Character-Level Click-Through Rate Prediction for Sponsored Search
Deep Character-Level Click-Through Rate Prediction for Sponsored Search Bora Edizel - Phd Student UPF Amin Mantrach - Criteo Research Xiao Bai - Oath This work was done at Yahoo and will be presented as
LEARNING TO INFER GRAPHICS PROGRAMS FROM HAND DRAWN IMAGES
LEARNING TO INFER GRAPHICS PROGRAMS FROM HAND DRAWN IMAGES Kevin Ellis - MIT, Daniel Ritchie - Brown University, Armando Solar-Lezama - MIT, Joshua b. Tenenbaum - MIT Presented by : Maliha Arif Advanced
With many contributors: A. Agarwal, E. Akchurin, C. Basoglu, G. Chen, S. Cyphers, W. Darling, J. Droppo, A. Eversole, B. Guenter, P. He, M.
With many contributors: A. Agarwal, E. Akchurin, C. Basoglu, G. Chen, S. Cyphers, W. Darling, J. Droppo, A. Eversole, B. Guenter, P. He, M. Hillebrand, X. Huang, Z. Huang, R. Hoens, V. Ivanov, A. Kamenev,
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
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,
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
Combining Neural Networks and Log-linear Models to Improve Relation Extraction
Combining Neural Networks and Log-linear Models to Improve Relation Extraction Thien Huu Nguyen and Ralph Grishman Computer Science Department, New York University {thien,grishman}@cs.nyu.edu Outline Relation
Multi-Class Logistic Regression and Perceptron
Multi-Class Logistic Regression and Perceptron Instructor: Wei Xu Some slides adapted from Dan Jurfasky, Brendan O Connor and Marine Carpuat MultiClass Classification Q: what if we have more than 2 categories?
CS 224N: Assignment #1
Due date: assignment) 1/25 11:59 PM PST (You are allowed to use three (3) late days maximum for this These questions require thought, but do not require long answers. Please be as concise as possible.
Asynchronous Parallel Learning for Neural Networks and Structured Models with Dense Features
Asynchronous Parallel Learning for Neural Networks and Structured Models with Dense Features Xu SUN ( 孙栩 ) Peking University xusun@pku.edu.cn Motivation Neural networks -> Good Performance CNN, RNN, LSTM
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
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
A Hybrid Neural Model for Type Classification of Entity Mentions
A Hybrid Neural Model for Type Classification of Entity Mentions Motivation Types group entities to categories Entity types are important for various NLP tasks Our task: predict an entity mention s type
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
Predicting your Next Stop-Over from Location-Based Social Network Data with Recurrent Neural Networks RecTour workshop 2017 RecSys 2017, Como, Italy
Predicting your Next Stop-Over from Location-Based Social Network Data with Recurrent Neural Networks RecTour workshop 217 RecSys 217, Como, Italy Enrico Palumbo, ISMB, Italy, Turin Giuseppe Rizzo, ISMB,
Mining Human Trajectory Data: A Study on Check-in Sequences. Xin Zhao Renmin University of China,
Mining Human Trajectory Data: A Study on Check-in Sequences Xin Zhao batmanfly@qq.com Renmin University of China, Check-in data What information these check-in data contain? User ID Location ID Check-in
Can Active Memory Replace Attention?
Google Brain NIPS 2016 Presenter: Chao Jiang NIPS 2016 Presenter: Chao Jiang 1 / Outline 1 Introduction 2 Active Memory 3 Step by Step to Neural GPU 4 Another two steps: 1. the Markovian Neural GPU 5 Another
CS 224d: Assignment #1
Due date: assignment) 4/19 11:59 PM PST (You are allowed to use three (3) late days maximum for this These questions require thought, but do not require long answers. Please be as concise as possible.
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
GraphNet: Recommendation system based on language and network structure
GraphNet: Recommendation system based on language and network structure Rex Ying Stanford University rexying@stanford.edu Yuanfang Li Stanford University yli03@stanford.edu Xin Li Stanford University xinli16@stanford.edu
CS 224N: Assignment #1
Due date: assignment) 1/25 11:59 PM PST (You are allowed to use three (3) late days maximum for this These questions require thought, but do not require long answers. Please be as concise as possible.
Recurrent Neural Network (RNN) Industrial AI Lab.
Recurrent Neural Network (RNN) Industrial AI Lab. For example (Deterministic) Time Series Data Closed- form Linear difference equation (LDE) and initial condition High order LDEs 2 (Stochastic) Time Series
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,
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
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
16-785: Integrated Intelligence in Robotics: Vision, Language, and Planning. Spring 2018 Lecture 14. Image to Text
16-785: Integrated Intelligence in Robotics: Vision, Language, and Planning Spring 2018 Lecture 14. Image to Text Input Output Classification tasks 4/1/18 CMU 16-785: Integrated Intelligence in Robotics
How to Develop Encoder-Decoder LSTMs
Chapter 9 How to Develop Encoder-Decoder LSTMs 9.0.1 Lesson Goal The goal of this lesson is to learn how to develop encoder-decoder LSTM models. completing this lesson, you will know: After ˆ The Encoder-Decoder
SEMANTIC COMPUTING. Lecture 8: Introduction to Deep Learning. TU Dresden, 7 December Dagmar Gromann International Center For Computational Logic
SEMANTIC COMPUTING Lecture 8: Introduction to Deep Learning Dagmar Gromann International Center For Computational Logic TU Dresden, 7 December 2018 Overview Introduction Deep Learning General Neural Networks
Natural Language Processing with Deep Learning CS224N/Ling284
Natural Language Processing with Deep Learning CS224N/Ling284 Lecture 8: Recurrent Neural Networks Christopher Manning and Richard Socher Organization Extra project office hour today after lecture Overview
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
Autoencoders. Stephen Scott. Introduction. Basic Idea. Stacked AE. Denoising AE. Sparse AE. Contractive AE. Variational AE GAN.
Stacked Denoising Sparse Variational (Adapted from Paul Quint and Ian Goodfellow) Stacked Denoising Sparse Variational Autoencoding is training a network to replicate its input to its output Applications:
COMP 551 Applied Machine Learning Lecture 14: Neural Networks
COMP 551 Applied Machine Learning Lecture 14: Neural Networks Instructor: (jpineau@cs.mcgill.ca) Class web page: www.cs.mcgill.ca/~jpineau/comp551 Unless otherwise noted, all material posted for this course
CS 224n: Assignment #3
CS 224n: Assignment #3 Due date: 2/27 11:59 PM PST (You are allowed to use 3 late days maximum for this assignment) These questions require thought, but do not require long answers. Please be as concise
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
Sequence Modeling: Recurrent and Recursive Nets. By Pyry Takala 14 Oct 2015
Sequence Modeling: Recurrent and Recursive Nets By Pyry Takala 14 Oct 2015 Agenda Why Recurrent neural networks? Anatomy and basic training of an RNN (10.2, 10.2.1) Properties of RNNs (10.2.2, 8.2.6) Using
Deep learning at Microsoft
Deep learning at Services Skype Translator Cortana Bing HoloLens Research Services ImageNet: 2015 ResNet 28.2 25.8 ImageNet Classification top-5 error (%) 16.4 11.7 7.3 6.7 3.5 ILSVRC 2010 NEC America
Deep Learning Benchmarks Mumtaz Vauhkonen, Quaizar Vohra, Saurabh Madaan Collaboration with Adam Coates, Stanford Unviersity
Deep Learning Benchmarks Mumtaz Vauhkonen, Quaizar Vohra, Saurabh Madaan Collaboration with Adam Coates, Stanford Unviersity Abstract: This project aims at creating a benchmark for Deep Learning (DL) algorithms
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
Facial Expression Classification with Random Filters Feature Extraction
Facial Expression Classification with Random Filters Feature Extraction Mengye Ren Facial Monkey mren@cs.toronto.edu Zhi Hao Luo It s Me lzh@cs.toronto.edu I. ABSTRACT In our work, we attempted to tackle
(Multinomial) Logistic Regression + Feature Engineering
-6 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University (Multinomial) Logistic Regression + Feature Engineering Matt Gormley Lecture 9 Feb.
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
JOINT INTENT DETECTION AND SLOT FILLING USING CONVOLUTIONAL NEURAL NETWORKS. Puyang Xu, Ruhi Sarikaya. Microsoft Corporation
JOINT INTENT DETECTION AND SLOT FILLING USING CONVOLUTIONAL NEURAL NETWORKS Puyang Xu, Ruhi Sarikaya Microsoft Corporation ABSTRACT We describe a joint model for intent detection and slot filling based
FastText. Jon Koss, Abhishek Jindal
FastText Jon Koss, Abhishek Jindal FastText FastText is on par with state-of-the-art deep learning classifiers in terms of accuracy But it is way faster: FastText can train on more than one billion words
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
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
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
CS 179 Lecture 16. Logistic Regression & Parallel SGD
CS 179 Lecture 16 Logistic Regression & Parallel SGD 1 Outline logistic regression (stochastic) gradient descent parallelizing SGD for neural nets (with emphasis on Google s distributed neural net implementation)
Multi-layer Perceptron Forward Pass Backpropagation. Lecture 11: Aykut Erdem November 2016 Hacettepe University
Multi-layer Perceptron Forward Pass Backpropagation Lecture 11: Aykut Erdem November 2016 Hacettepe University Administrative Assignment 2 due Nov. 10, 2016! Midterm exam on Monday, Nov. 14, 2016 You are
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
Sayan Pathak Principal ML Scientist. Chris Basoglu Partner Dev Manager
Sayan Pathak Principal ML Scientist Chris Basoglu Partner Dev Manager With many contributors: A. Agarwal, E. Akchurin, E. Barsoum, C. Basoglu, G. Chen, S. Cyphers, W. Darling, J. Droppo, K. Deng, A. Eversole,
Neural Network Models for Text Classification. Hongwei Wang 18/11/2016
Neural Network Models for Text Classification Hongwei Wang 18/11/2016 Deep Learning in NLP Feedforward Neural Network The most basic form of NN Convolutional Neural Network (CNN) Quite successful in computer
Show, Discriminate, and Tell: A Discriminatory Image Captioning Model with Deep Neural Networks
Show, Discriminate, and Tell: A Discriminatory Image Captioning Model with Deep Neural Networks Zelun Luo Department of Computer Science Stanford University zelunluo@stanford.edu Te-Lin Wu Department of
XES Tensorflow Process Prediction using the Tensorflow Deep-Learning Framework
XES Tensorflow Process Prediction using the Tensorflow Deep-Learning Framework Demo Paper Joerg Evermann 1, Jana-Rebecca Rehse 2,3, and Peter Fettke 2,3 1 Memorial University of Newfoundland 2 German Research
Mini-project 2 CMPSCI 689 Spring 2015 Due: Tuesday, April 07, in class
Mini-project 2 CMPSCI 689 Spring 2015 Due: Tuesday, April 07, in class Guidelines Submission. Submit a hardcopy of the report containing all the figures and printouts of code in class. For readability
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
The exam is closed book, closed notes except your one-page (two-sided) cheat sheet.
CS 189 Spring 2015 Introduction to Machine Learning Final You have 2 hours 50 minutes for the exam. The exam is closed book, closed notes except your one-page (two-sided) cheat sheet. No calculators or
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
Introduction to Deep Learning for Facial Understanding Part III: Regional CNNs
Introduction to Deep Learning for Facial Understanding Part III: Regional CNNs Raymond Ptucha, Rochester Institute of Technology, USA Tutorial-9 May 19, 218 www.nvidia.com/dli R. Ptucha 18 1 Fair Use Agreement
Simple Model Selection Cross Validation Regularization Neural Networks
Neural Nets: Many possible refs e.g., Mitchell Chapter 4 Simple Model Selection Cross Validation Regularization Neural Networks Machine Learning 10701/15781 Carlos Guestrin Carnegie Mellon University February
Slide credit from Hung-Yi Lee & Richard Socher
Slide credit from Hung-Yi Lee & Richard Socher 1 Review Word Vector 2 Word2Vec Variants Skip-gram: predicting surrounding words given the target word (Mikolov+, 2013) CBOW (continuous bag-of-words): predicting
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
Multinomial Regression and the Softmax Activation Function. Gary Cottrell!
Multinomial Regression and the Softmax Activation Function Gary Cottrell Notation reminder We have N data points, or patterns, in the training set, with the pattern number as a superscript: {(x 1,t 1 ),
Final Report: Classification of Plankton Classes By Tae Ho Kim and Saaid Haseeb Arshad
Final Report: Classification of Plankton Classes By Tae Ho Kim and Saaid Haseeb Arshad Table of Contents 1. Project Overview a. Problem Statement b. Data c. Overview of the Two Stages of Implementation
Artificial Intelligence Introduction Handwriting Recognition Kadir Eren Unal ( ), Jakob Heyder ( )
Structure: 1. Introduction 2. Problem 3. Neural network approach a. Architecture b. Phases of CNN c. Results 4. HTM approach a. Architecture b. Setup c. Results 5. Conclusion 1.) Introduction Artificial
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
Seq2SQL: Generating Structured Queries from Natural Language Using Reinforcement Learning
Seq2SQL: Generating Structured Queries from Natural Language Using Reinforcement Learning V. Zhong, C. Xiong, R. Socher Salesforce Research arxiv: 1709.00103 Reviewed by : Bill Zhang University of Virginia
Programming Projects
Programming Projects Benjamin Roth, Nina Poerner, Anne Beyer Centrum für Informations- und Sprachverarbeitung Ludwig-Maximilian-Universität München beroth@cis.uni-muenchen.de Benjamin Roth, Nina Poerner,
Lecture : Training a neural net part I Initialization, activations, normalizations and other practical details Anne Solberg February 28, 2018
INF 5860 Machine learning for image classification Lecture : Training a neural net part I Initialization, activations, normalizations and other practical details Anne Solberg February 28, 2018 Reading
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
A Simple (?) Exercise: Predicting the Next Word
CS11-747 Neural Networks for NLP A Simple (?) Exercise: Predicting the Next Word Graham Neubig Site https://phontron.com/class/nn4nlp2017/ Are These Sentences OK? Jane went to the store. store to Jane
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
S-MART: Novel Tree-based Structured Learning Algorithms Applied to Tweet Entity Linking
S-MART: Novel Tree-based Structured Learning Algorithms Applied to Tweet Entity Linking Yi Yang * and Ming-Wei Chang # * Georgia Institute of Technology, Atlanta # Microsoft Research, Redmond Traditional
EECS 496 Statistical Language Models. Winter 2018
EECS 496 Statistical Language Models Winter 2018 Introductions Professor: Doug Downey Course web site: www.cs.northwestern.edu/~ddowney/courses/496_winter2018 (linked off prof. home page) Logistics Grading
Contents Machine Learning concepts 4 Learning Algorithm 4 Predictive Model (Model) 4 Model, Classification 4 Model, Regression 4 Representation
Contents Machine Learning concepts 4 Learning Algorithm 4 Predictive Model (Model) 4 Model, Classification 4 Model, Regression 4 Representation Learning 4 Supervised Learning 4 Unsupervised Learning 4
Hello Edge: Keyword Spotting on Microcontrollers
Hello Edge: Keyword Spotting on Microcontrollers Yundong Zhang, Naveen Suda, Liangzhen Lai and Vikas Chandra ARM Research, Stanford University arxiv.org, 2017 Presented by Mohammad Mofrad University of
Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN) By Prof. Seungchul Lee Industrial AI Lab http://isystems.unist.ac.kr/ POSTECH Table of Contents I. 1. Convolution on Image I. 1.1. Convolution in 1D II. 1.2. Convolution
CS 1674: Intro to Computer Vision. Neural Networks. Prof. Adriana Kovashka University of Pittsburgh November 16, 2016
CS 1674: Intro to Computer Vision Neural Networks Prof. Adriana Kovashka University of Pittsburgh November 16, 2016 Announcements Please watch the videos I sent you, if you haven t yet (that s your reading)
Gate-Variants of Gated Recurrent Unit (GRU) Neural Networks
Gate-Variants of Gated Recurrent Unit (GRU) Neural Networks Rahul Dey and Fathi M. Salem Circuits, Systems, and Neural Networks (CSANN) LAB Department of Electrical and Computer Engineering Michigan State
Deep Learning. Volker Tresp Summer 2014
Deep Learning Volker Tresp Summer 2014 1 Neural Network Winter and Revival While Machine Learning was flourishing, there was a Neural Network winter (late 1990 s until late 2000 s) Around 2010 there
Machine Learning. Topic 5: Linear Discriminants. Bryan Pardo, EECS 349 Machine Learning, 2013
Machine Learning Topic 5: Linear Discriminants Bryan Pardo, EECS 349 Machine Learning, 2013 Thanks to Mark Cartwright for his extensive contributions to these slides Thanks to Alpaydin, Bishop, and Duda/Hart/Stork
Query Intent Detection using Convolutional Neural Networks
Query Intent Detection using Convolutional Neural Networks Homa B. Hashemi, Amir Asiaee, Reiner Kraft QRUMS workshop - February 22, 2016 Query Intent Detection michelle obama age Query Intent Detection
Opportunities and challenges in personalization of online hotel search
Opportunities and challenges in personalization of online hotel search David Zibriczky Data Science & Analytics Lead, User Profiling Introduction 2 Introduction About Mission: Helping the travelers to
End-To-End Spam Classification With Neural Networks
End-To-End Spam Classification With Neural Networks Christopher Lennan, Bastian Naber, Jan Reher, Leon Weber 1 Introduction A few years ago, the majority of the internet s network traffic was due to spam
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
Core ML in Depth. System Frameworks #WWDC17. Krishna Sridhar, Core ML Zach Nation, Core ML
System Frameworks #WWDC17 Core ML in Depth Krishna Sridhar, Core ML Zach Nation, Core ML 2017 Apple Inc. All rights reserved. Redistribution or public display not permitted without written permission from
Pointer Network. Oriol Vinyals. 박천음 강원대학교 Intelligent Software Lab.
Pointer Network Oriol Vinyals 박천음 강원대학교 Intelligent Software Lab. Intelligent Software Lab. Pointer Network 1 Pointer Network 2 Intelligent Software Lab. 2 Sequence-to-Sequence Model Train 학습학습학습학습학습 Test