Conditional Image Generation with PixelCNN Decoders
|
|
|
- Barbra Hill
- 6 years ago
- Views:
Transcription
1 Conditional Image Generation with PixelCNN Decoders Aaron van den Oord 1 Nal Kalchbrenner 1 Oriol Vinyals 1 Lasse Espeholt 1 Alex Graves 1 Koray Kavukcuoglu 1 1 Google DeepMind NIPS, 2016 Presenter: Beilun Wang NIPS, 2016 Presenter: Beilun Wang 1 / Aaron van den Oord, Nal Kalchbrenner, OriolConditional Vinyals, Lasse Image Espeholt, Generation Alex with Graves, PixelCNN Koray Kavukcuoglu Decoders (Google DeepMind) 21
2 Outline 1 Introduction Motivation Previous Solutions Contributions 2 Proposed Methods PixelCNN Conditional PixelCNN 3 Summary NIPS, 2016 Presenter: Beilun Wang 2 / Aaron van den Oord, Nal Kalchbrenner, OriolConditional Vinyals, Lasse Image Espeholt, Generation Alex with Graves, PixelCNN Koray Kavukcuoglu Decoders (Google DeepMind) 21
3 Outline 1 Introduction Motivation Previous Solutions Contributions 2 Proposed Methods PixelCNN Conditional PixelCNN 3 Summary NIPS, 2016 Presenter: Beilun Wang 3 / Aaron van den Oord, Nal Kalchbrenner, OriolConditional Vinyals, Lasse Image Espeholt, Generation Alex with Graves, PixelCNN Koray Kavukcuoglu Decoders (Google DeepMind) 21
4 Motivation Motivation: Conditional image generator with image density model. This generator can also be conditioned on class labels, descriptions and a single human face. Fast and parallel training. NIPS, 2016 Presenter: Beilun Wang 4 / Aaron van den Oord, Nal Kalchbrenner, OriolConditional Vinyals, Lasse Image Espeholt, Generation Alex with Graves, PixelCNN Koray Kavukcuoglu Decoders (Google DeepMind) 21
5 Problem Setting: Problem Setting: Input: Image with missing pixels, OR image class labels, OR a vector in the embedded space, OR a single human face Target: joint distribution consisting of conditional distribution with CNN. Output: Image PixelCNN (Pixel RNN): Conditional Version: p(x) = p(x i x 1,..., x i 1 ) (1) n 2 i=1 p(x h) = p(x i x 1,..., x i 1, h) (2) n 2 i=1 B conditioned on (R,G); G conditioned on R. NIPS, 2016 Presenter: Beilun Wang 5 / Aaron van den Oord, Nal Kalchbrenner, OriolConditional Vinyals, Lasse Image Espeholt, Generation Alex with Graves, PixelCNN Koray Kavukcuoglu Decoders (Google DeepMind) 21
6 Outline 1 Introduction Motivation Previous Solutions Contributions 2 Proposed Methods PixelCNN Conditional PixelCNN 3 Summary NIPS, 2016 Presenter: Beilun Wang 6 / Aaron van den Oord, Nal Kalchbrenner, OriolConditional Vinyals, Lasse Image Espeholt, Generation Alex with Graves, PixelCNN Koray Kavukcuoglu Decoders (Google DeepMind) 21
7 Previous Solutions PixelRNN Figure: PixelRNN NIPS, 2016 Presenter: Beilun Wang 7 / Aaron van den Oord, Nal Kalchbrenner, OriolConditional Vinyals, Lasse Image Espeholt, Generation Alex with Graves, PixelCNN Koray Kavukcuoglu Decoders (Google DeepMind) 21
8 Outline 1 Introduction Motivation Previous Solutions Contributions 2 Proposed Methods PixelCNN Conditional PixelCNN 3 Summary NIPS, 2016 Presenter: Beilun Wang 8 / Aaron van den Oord, Nal Kalchbrenner, OriolConditional Vinyals, Lasse Image Espeholt, Generation Alex with Graves, PixelCNN Koray Kavukcuoglu Decoders (Google DeepMind) 21
9 Contributions A fast and parallel trainable deep neural nets model for conditional image generator (?) Gated convolutional layers Conditional Gated convolutional layers NIPS, 2016 Presenter: Beilun Wang 9 / Aaron van den Oord, Nal Kalchbrenner, OriolConditional Vinyals, Lasse Image Espeholt, Generation Alex with Graves, PixelCNN Koray Kavukcuoglu Decoders (Google DeepMind) 21
10 Outline 1 Introduction Motivation Previous Solutions Contributions 2 Proposed Methods PixelCNN Conditional PixelCNN 3 Summary NIPS, 2016 Presenter: Beilun Wang 10
11 Pixel CNN Input: N N 3 Output: N N Figure: PixelCNN Only above and left Pixels are considered. NIPS, 2016 Presenter: Beilun Wang 11
12 Masked Filter NIPS, 2016 Presenter: Beilun Wang 12
13 Blind spot NIPS, 2016 Presenter: Beilun Wang 13
14 Gated Convolutional Layers The gates in LSTM may help it to model more complex interactions. This is also studied by paper like Highway networks, grid LSTM, and Neural GPUs. y = tanh(w k,f x) σ(w k,g x) (3) NIPS, 2016 Presenter: Beilun Wang 14
15 Gated Convolutional Layers figure Figure: Gated Convolutional Layers NIPS, 2016 Presenter: Beilun Wang 15
16 Outline 1 Introduction Motivation Previous Solutions Contributions 2 Proposed Methods PixelCNN Conditional PixelCNN 3 Summary NIPS, 2016 Presenter: Beilun Wang 16
17 Conditional PixelCNN replace p(x h) from p(x). y = tanh(w k,f x + Vk,f T h) σ(w k,g x + Vk,g T h) (4) NIPS, 2016 Presenter: Beilun Wang 17
18 Conditional PixelCNN Embedded Use a deconvolutional neural nets m() map h back to the image space as s y = tanh(w k,f x + Vk,f T s) σ(w k,g x + Vk,g T s) (5) NIPS, 2016 Presenter: Beilun Wang 18
19 Experiment Results image generation based on labels NIPS, 2016 Presenter: Beilun Wang 19 Aaron van den Oord, Nal Kalchbrenner, Oriol Conditional Vinyals, Lasse Image Espeholt, Generation Alex with Graves, PixelCNN Koray Kavukcuoglu Decoders (Google DeepMind) / 21
20 Experiment Results image generation based on a single human face NIPS, 2016 Presenter: Beilun Wang 20
21 Summary This paper improves the PixelCNN by the gated activation unit This paper extends the PixelCNN to a conditional version NIPS, 2016 Presenter: Beilun Wang 21
arxiv: v1 [cs.lg] 28 Dec 2017
![arxiv: v1 [cs.lg] 28 Dec 2017](/thumbs/80/82263025.jpg "arxiv: v1 [cs.lg] 28 Dec 2017")
PixelSNAIL: An Improved Autoregressive Generative Model arxiv:1712.09763v1 [cs.lg] 28 Dec 2017 Xi Chen, Nikhil Mishra, Mostafa Rohaninejad, Pieter Abbeel Embodied Intelligence UC Berkeley, Department of
WaveNet: A Generative Model for Raw Audio
WaveNet: A Generative Model for Raw Audio Ido Guy & Daniel Brodeski Deep Learning Seminar 2017 TAU Outline Introduction WaveNet Experiments Introduction WaveNet is a deep generative model of raw audio
CSC321 Lecture 20: Reversible and Autoregressive Models
CSC321 Lecture 20: Reversible and Autoregressive Models Roger Grosse Roger Grosse CSC321 Lecture 20: Reversible and Autoregressive Models 1 / 23 Overview Four modern approaches to generative modeling:
Pixel Recurrent Neural Networks
Pixel Recurret Neural Networks Aa ro va de Oord, Nal Kalchbreer, Koray Kavukcuoglu Google DeepMid August 2016 Preseter - Neha M Example problem (completig a image) Give the first half of the image, create
Machine Translation. 10: Advanced Neural Machine Translation Architectures. Rico Sennrich. University of Edinburgh. R. Sennrich MT / 26
Machine Translation 10: Advanced Neural Machine Translation Architectures Rico Sennrich University of Edinburgh R. Sennrich MT 2018 10 1 / 26 Today s Lecture so far today we discussed RNNs as encoder and
Deep Learning Year in Review 2016: Computer Vision Perspective
Deep Learning Year in Review 2016: Computer Vision Perspective Alex Kalinin, PhD Candidate Bioinformatics @ UMich alxndrkalinin@gmail.com @alxndrkalinin Architectures Summary of CNN architecture development
Today s Lecture. Dropout
Today s Lecture so far we discussed RNNs as encoder and decoder we discussed some architecture variants: RNN vs. GRU vs. LSTM attention mechanisms Machine Translation 1: Advanced Neural Machine Translation
CKY-based Convolutional Attention for Neural Machine Translation
CKY-based Convolutional Attention for Neural Machine Translation Taiki Watanabe and Akihiro Tamura and Takashi Ninomiya Ehime University 3 Bunkyo-cho, Matsuyama, Ehime, JAPAN {t_watanabe@ai.cs, tamura@cs,
Self-Attention with Relative Position Representations
Self-Attention with Relative Position Representations Peter Shaw Google petershaw@google.com Jakob Uszkoreit Google Brain usz@google.com Ashish Vaswani Google Brain avaswani@google.com Abstract Relying
Recurrent Neural Network
Recurrent Neural Network Xiaogang Wang xgwang@ee..edu.hk March 2, 2017 Xiaogang Wang (linux) Recurrent Neural Network March 2, 2017 1 / 48 Outline 1 Recurrent neural networks Recurrent neural networks
Lecture 9 Recurrent Neural Networks
Lecture 9 Recurrent Neural Networks I m glad that I m Turing Complete now Xinyu Zhou Megvii (Face++) Researcher zxy@megvii.com Nov 2017 Raise your hand and ask, whenever you have questions... We have a
PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs
PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs Yunbo Wang School of Software Tsinghua University wangyb15@mails.tsinghua.edu.cn Mingsheng Long School of Software
arxiv: v1 [cs.lg] 2 Nov 2017
![arxiv: v1 [cs.lg] 2 Nov 2017](/thumbs/76/74017029.jpg "arxiv: v1 [cs.lg] 2 Nov 2017")
Neural Discrete Representation Learning Aaron van den Oord DeepMind avdnoord@google.com Oriol Vinyals DeepMind vinyals@google.com Koray Kavukcuoglu DeepMind korayk@google.com arxiv:1711.00937v1 [cs.lg]
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
arxiv: v2 [cs.lg] 4 Mar 2017
![arxiv: v2 [cs.lg] 4 Mar 2017](/thumbs/74/70632048.jpg "arxiv: v2 [cs.lg] 4 Mar 2017")
VARIATIONAL LOSSY AUTOENCODER Xi Chen, Diederik P. Kingma, Tim Salimans, Yan Duan, Prafulla Dhariwal, John Schulman, Ilya Sutskever, Pieter Abbeel UC Berkeley, Department of Electrical Engineering and
arxiv: v2 [cs.lg] 11 Jun 2018
![arxiv: v2 [cs.lg] 11 Jun 2018](/thumbs/89/98764675.jpg "arxiv: v2 [cs.lg] 11 Jun 2018")
Temporal Difference Variational Auto-Encoder Karol Gregor DeepMind karolg@google.com Frederic Besse DeepMind fbesse@google.com arxiv:1806.03107v2 [cs.lg] 11 Jun 2018 Abstract One motivation for learning
High Order LSTM/GRU. Wenjie Luo. January 19, 2016
High Order LSTM/GRU Wenjie Luo January 19, 2016 1 Introduction RNN is a powerful model for sequence data but suffers from gradient vanishing and explosion, thus difficult to be trained to capture long
Spatial Transformer. Ref: Max Jaderberg, Karen Simonyan, Andrew Zisserman, Koray Kavukcuoglu, Spatial Transformer Networks, NIPS, 2015
Spatial Transormer Re: Max Jaderberg, Karen Simonyan, Andrew Zisserman, Koray Kavukcuoglu, Spatial Transormer Networks, NIPS, 2015 Spatial Transormer Layer CNN is not invariant to scaling and rotation
Machine Learning for Signal Processing Neural Networks Continue. Instructor: Bhiksha Raj Slides by Najim Dehak 1 Dec 2016
Machine Learning for Signal Processing Neural Networks Continue Instructor: Bhiksha Raj Slides by Najim Dehak 1 Dec 2016 1 So what are neural networks?? Voice signal N.Net Transcription Image N.Net Text
FAST ADAPTATION IN GENERATIVE MODELS WITH GENERATIVE MATCHING NETWORKS
FAST ADAPTATION IN GENERATIVE MODELS WITH GENERATIVE MATCHING NETWORKS Sergey Bartunov & Dmitry P. Vetrov National Research University Higher School of Economics (HSE), Yandex Moscow, Russia ABSTRACT We
The Success of Deep Generative Models
The Success of Deep Generative Models Jakub Tomczak AMLAB, University of Amsterdam CERN, 2018 What is AI about? What is AI about? Decision making: What is AI about? Decision making: new data High probability
Neural Architectures for Image, Language, and Speech Processing
Neural Architectures for Image, Language, and Speech Processing Karl Stratos June 26, 2018 1 / 31 Overview Feedforward Networks Need for Specialized Architectures Convolutional Neural Networks (CNNs) Recurrent
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
Masked Autoregressive Flow for Density Estimation
Masked Autoregressive Flow for Density Estimation George Papamakarios University of Edinburgh g.papamakarios@ed.ac.uk Theo Pavlakou University of Edinburgh theo.pavlakou@ed.ac.uk Iain Murray University
Dimensionality Reduction and Principle Components Analysis
Dimensionality Reduction and Principle Components Analysis 1 Outline What is dimensionality reduction? Principle Components Analysis (PCA) Example (Bishop, ch 12) PCA vs linear regression PCA as a mixture
Autoregressive Attention for Parallel Sequence Modeling
Autoregressive Attention for Parallel Sequence Modeling Dillon Laird Department of Computer Science Stanford University Stanford, CA 94305 dalaird@cs.stanford.edu Jeremy Irvin Department of Computer Science
Improving Variational Inference with Inverse Autoregressive Flow
Improving Variational Inference with Inverse Autoregressive Flow Diederik P. Kingma dpkingma@openai.com Tim Salimans tim@openai.com Rafal Jozefowicz rafal@openai.com Xi Chen peter@openai.com Ilya Sutskever
Parallel WaveNet: Fast High-Fidelity Speech Synthesis
Parallel WaveNet: Fast High-Fidelity Speech Synthesis Aaron van den Oord, Yazhe Li, Igor Babuschkin, Karen Simonyan, Oriol Vinyals, Koray Kavukcuoglu avdnoord,yazhe,ibab,simonyan,vinyals,korayk@google.com
PARALLELIZING LINEAR RECURRENT NEURAL NETS OVER SEQUENCE LENGTH
PARALLELIZING LINEAR RECURRENT NEURAL NETS OVER SEQUENCE LENGTH Eric Martin eric@ericmart.in Chris Cundy Department of Computer Science University of California, Berkeley Berkeley, CA 94720, USA c.cundy@berkeley.edu
arxiv: v2 [cs.cl] 16 Jun 2017 Abstract
![arxiv: v2 [cs.cl] 16 Jun 2017 Abstract](/thumbs/76/73865563.jpg "arxiv: v2 [cs.cl] 16 Jun 2017 Abstract")
Depthwise Separable Convolutions for Neural Machine Translation Łukasz Kaiser Google Brain lukaszkaiser@google.com Aidan N. Gomez University of Toronto aidan@cs.toronto.edu François Chollet Google Brain
Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction
Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction Maha Elbayad 1,2 Laurent Besacier 1 Jakob Verbeek 2 Univ. Grenoble Alpes, CNRS, Grenoble INP, Inria, LIG, LJK,
Deep Learning. Recurrent Neural Network (RNNs) Ali Ghodsi. October 23, Slides are partially based on Book in preparation, Deep Learning
Recurrent Neural Network (RNNs) University of Waterloo October 23, 2015 Slides are partially based on Book in preparation, by Bengio, Goodfellow, and Aaron Courville, 2015 Sequential data Recurrent neural
Full Resolution Image Compression with Recurrent Neural Networks
Full Resolution Image Compression with Recurrent Neural Networks George Toderici Google Research Damien Vincent damienv@google.com Nick Johnston nickj@google.com Sung Jin Hwang sjhwang@google.com gtoderici@google.com
Generating Text via Adversarial Training
Generating Text via Adversarial Training Yizhe Zhang, Zhe Gan, Lawrence Carin Department of Electronical and Computer Engineering Duke University, Durham, NC 27708 {yizhe.zhang,zhe.gan,lcarin}@duke.edu
Modeling Time-Frequency Patterns with LSTM vs. Convolutional Architectures for LVCSR Tasks
Modeling Time-Frequency Patterns with LSTM vs Convolutional Architectures for LVCSR Tasks Tara N Sainath, Bo Li Google, Inc New York, NY, USA {tsainath, boboli}@googlecom Abstract Various neural network
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»
TTIC 31230, Fundamentals of Deep Learning David McAllester, April Vanishing and Exploding Gradients. ReLUs. Xavier Initialization
TTIC 31230, Fundamentals of Deep Learning David McAllester, April 2017 Vanishing and Exploding Gradients ReLUs Xavier Initialization Batch Normalization Highway Architectures: Resnets, LSTMs and GRUs Causes
Deep Learning and Lexical, Syntactic and Semantic Analysis. Wanxiang Che and Yue Zhang
Deep Learning and Lexical, Syntactic and Semantic Analysis Wanxiang Che and Yue Zhang 2016-10 Part 2: Introduction to Deep Learning Part 2.1: Deep Learning Background What is Machine Learning? From Data
Character-Level Language Modeling with Recurrent Highway Hypernetworks
Character-Level Language Modeling with Recurrent Highway Hypernetworks Joseph Suarez Stanford University joseph15@stanford.edu Abstract We present extensive experimental and theoretical support for the
Generative Adversarial Networks
Generative Adversarial Networks SIBGRAPI 2017 Tutorial Everything you wanted to know about Deep Learning for Computer Vision but were afraid to ask Presentation content inspired by Ian Goodfellow s tutorial
Recurrent Neural Networks (RNN) and Long-Short-Term-Memory (LSTM) Yuan YAO HKUST
1 Recurrent Neural Networks (RNN) and Long-Short-Term-Memory (LSTM) Yuan YAO HKUST Summary We have shown: Now First order optimization methods: GD (BP), SGD, Nesterov, Adagrad, ADAM, RMSPROP, etc. Second
Sum-Product-Quotient Networks
Or Sharir The Hebrew University of Jerusalem or.sharir@cs.huji.ac.il Amnon Shashua The Hebrew University of Jerusalem shashua@cs.huji.ac.il Abstract We present a novel tractable generative model that extends
arxiv: v1 [stat.ml] 18 Nov 2017
![arxiv: v1 [stat.ml] 18 Nov 2017](/thumbs/72/67293632.jpg "arxiv: v1 [stat.ml] 18 Nov 2017")
MinimalRNN: Toward More Interpretable and Trainable Recurrent Neural Networks arxiv:1711.06788v1 [stat.ml] 18 Nov 2017 Minmin Chen Google Mountain view, CA 94043 minminc@google.com Abstract We introduce
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
arxiv: v1 [cs.lg] 15 Jun 2016
![arxiv: v1 [cs.lg] 15 Jun 2016](/thumbs/86/93343117.jpg "arxiv: v1 [cs.lg] 15 Jun 2016")
Improving Variational Inference with Inverse Autoregressive Flow arxiv:1606.04934v1 [cs.lg] 15 Jun 2016 Diederik P. Kingma, Tim Salimans and Max Welling OpenAI, San Francisco University of Amsterdam, University
Deep Learning for Automatic Speech Recognition Part II
Deep Learning for Automatic Speech Recognition Part II Xiaodong Cui IBM T. J. Watson Research Center Yorktown Heights, NY 10598 Fall, 2018 Outline A brief revisit of sampling, pitch/formant and MFCC DNN-HMM
a) b) (Natural Language Processing; NLP) (Deep Learning) Bag of words White House RGB [1] IBM
![a) b) (Natural Language Processing; NLP) (Deep Learning) Bag of words White House RGB [1] IBM](/thumbs/92/107948882.jpg "a) b) (Natural Language Processing; NLP) (Deep Learning) Bag of words White House RGB [1] IBM")
c 1. (Natural Language Processing; NLP) (Deep Learning) RGB IBM 135 8511 5 6 52 yutat@jp.ibm.com a) b) 2. 1 0 2 1 Bag of words White House 2 [1] 2015 4 Copyright c by ORSJ. Unauthorized reproduction of
Lecture 8: Recurrent Neural Networks
Lecture 8: Recurrent Neural Networks André Martins Deep Structured Learning Course, Fall 2018 André Martins (IST) Lecture 8 IST, Fall 2018 1 / 85 Announcements The deadline for the project midterm report
DO DEEP GENERATIVE MODELS KNOW WHAT THEY DON T KNOW?
DO DEEP GENERATIVE MODELS KNOW WHAT THEY DON T KNOW? Eric Nalisnick, Akihiro Matsukawa, Yee Whye Teh, Dilan Gorur, Balaji Lakshminarayanan DeepMind ABSTRACT A neural network deployed in the wild may be
Presented By: Omer Shmueli and Sivan Niv
Deep Speaker: an End-to-End Neural Speaker Embedding System Chao Li, Xiaokong Ma, Bing Jiang, Xiangang Li, Xuewei Zhang, Xiao Liu, Ying Cao, Ajay Kannan, Zhenyao Zhu Presented By: Omer Shmueli and Sivan
Unsupervised Learning of Hierarchical Models. in collaboration with Josh Susskind and Vlad Mnih
Unsupervised Learning of Hierarchical Models Marc'Aurelio Ranzato Geoff Hinton in collaboration with Josh Susskind and Vlad Mnih Advanced Machine Learning, 9 March 2011 Example: facial expression recognition
Generating Sequences with Recurrent Neural Networks
Generating Sequences with Recurrent Neural Networks Alex Graves University of Toronto & Google DeepMind Presented by Zhe Gan, Duke University May 15, 2015 1 / 23 Outline Deep recurrent neural network based
WEIGHTED TRANSFORMER NETWORK FOR MACHINE TRANSLATION
WEIGHTED TRANSFORMER NETWORK FOR MACHINE TRANSLATION Anonymous authors Paper under double-blind review ABSTRACT State-of-the-art results on neural machine translation often use attentional sequence-to-sequence
MULTIPLICATIVE LSTM FOR SEQUENCE MODELLING
MULTIPLICATIVE LSTM FOR SEQUENCE MODELLING Ben Krause, Iain Murray & Steve Renals School of Informatics, University of Edinburgh Edinburgh, Scotland, UK {ben.krause,i.murray,s.renals}@ed.ac.uk Liang Lu
Structured deep models: Deep learning on graphs and beyond
Structured deep models: Deep learning on graphs and beyond Hidden layer Hidden layer Input Output ReLU ReLU, 25 May 2018 CompBio Seminar, University of Cambridge In collaboration with Ethan Fetaya, Rianne
Deep Learning Architectures and Algorithms
Deep Learning Architectures and Algorithms In-Jung Kim 2016. 12. 2. Agenda Introduction to Deep Learning RBM and Auto-Encoders Convolutional Neural Networks Recurrent Neural Networks Reinforcement Learning
Deep Q-Learning with Recurrent Neural Networks
Deep Q-Learning with Recurrent Neural Networks Clare Chen cchen9@stanford.edu Vincent Ying vincenthying@stanford.edu Dillon Laird dalaird@cs.stanford.edu Abstract Deep reinforcement learning models have
CS230: Lecture 8 Word2Vec applications + Recurrent Neural Networks with Attention
CS23: Lecture 8 Word2Vec applications + Recurrent Neural Networks with Attention Today s outline We will learn how to: I. Word Vector Representation i. Training - Generalize results with word vectors -
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
arxiv: v1 [stat.ml] 3 Nov 2016
![arxiv: v1 [stat.ml] 3 Nov 2016](/thumbs/94/121641111.jpg "arxiv: v1 [stat.ml] 3 Nov 2016")
CATEGORICAL REPARAMETERIZATION WITH GUMBEL-SOFTMAX Eric Jang Google Brain ejang@google.com Shixiang Gu University of Cambridge MPI Tübingen Google Brain sg717@cam.ac.uk Ben Poole Stanford University poole@cs.stanford.edu
Learning Semantic Prediction using Pretrained Deep Feedforward Networks
Learning Semantic Prediction using Pretrained Deep Feedforward Networks Jörg Wagner 1,2, Volker Fischer 1, Michael Herman 1 and Sven Behnke 2 1- Robert Bosch GmbH - 70442 Stuttgart - Germany 2- University
arxiv: v1 [cs.sd] 31 Oct 2018
![arxiv: v1 [cs.sd] 31 Oct 2018](/thumbs/92/108029045.jpg "arxiv: v1 [cs.sd] 31 Oct 2018")
WAVEGLOW: A FLOW-BASED GENERATIVE NETWORK FOR SPEECH SYNTHESIS Ryan Prenger, Rafael Valle, Bryan Catanzaro NVIDIA Corporation arxiv:1811.00002v1 [cs.sd] 31 Oct 2018 ABSTRACT In this paper we propose WaveGlow:
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
Residual LSTM: Design of a Deep Recurrent Architecture for Distant Speech Recognition
INTERSPEECH 017 August 0 4, 017, Stockholm, Sweden Residual LSTM: Design of a Deep Recurrent Architecture for Distant Speech Recognition Jaeyoung Kim 1, Mostafa El-Khamy 1, Jungwon Lee 1 1 Samsung Semiconductor,
Deep Generative Models for Graph Generation. Jian Tang HEC Montreal CIFAR AI Chair, Mila
Deep Generative Models for Graph Generation Jian Tang HEC Montreal CIFAR AI Chair, Mila Email: jian.tang@hec.ca Deep Generative Models Goal: model data distribution p(x) explicitly or implicitly, where
Deep Reinforcement Learning. Scratching the surface
Deep Reinforcement Learning Scratching the surface Deep Reinforcement Learning Scenario of Reinforcement Learning Observation State Agent Action Change the environment Don t do that Reward Environment
Recurrent Neural Networks with Flexible Gates using Kernel Activation Functions
2018 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 18) Recurrent Neural Networks with Flexible Gates using Kernel Activation Functions Authors: S. Scardapane, S. Van Vaerenbergh,
Contents. (75pts) COS495 Midterm. (15pts) Short answers
Contents (75pts) COS495 Midterm 1 (15pts) Short answers........................... 1 (5pts) Unequal loss............................. 2 (15pts) About LSTMs........................... 3 (25pts) Modular
Deep Sequence Models. Context Representation, Regularization, and Application to Language. Adji Bousso Dieng
Deep Sequence Models Context Representation, Regularization, and Application to Language Adji Bousso Dieng All Data Are Born Sequential Time underlies many interesting human behaviors. Elman, 1990. Why
Comparing Recent Waveform Generation and Acoustic Modeling Methods for Neural-network-based Speech Synthesis
ICASSP 2018 Calgary, Canada Comparing Recent Waveform Generation and Acoustic Modeling Methods for Neural-network-based Speech Synthesis Xin WANG, Jaime Lorenzo-Trueba, Shinji TAKAKI, Lauri Juvela, Junichi
Lecture 17: Neural Networks and Deep Learning
UVA CS 6316 / CS 4501-004 Machine Learning Fall 2016 Lecture 17: Neural Networks and Deep Learning Jack Lanchantin Dr. Yanjun Qi 1 Neurons 1-Layer Neural Network Multi-layer Neural Network Loss Functions
Neural Turing Machine. Author: Alex Graves, Greg Wayne, Ivo Danihelka Presented By: Tinghui Wang (Steve)
Neural Turing Machine Author: Alex Graves, Greg Wayne, Ivo Danihelka Presented By: Tinghui Wang (Steve) Introduction Neural Turning Machine: Couple a Neural Network with external memory resources The combined
arxiv: v1 [cs.cl] 21 May 2017
![arxiv: v1 [cs.cl] 21 May 2017](/thumbs/92/109535705.jpg "arxiv: v1 [cs.cl] 21 May 2017")
Spelling Correction as a Foreign Language Yingbo Zhou yingbzhou@ebay.com Utkarsh Porwal uporwal@ebay.com Roberto Konow rkonow@ebay.com arxiv:1705.07371v1 [cs.cl] 21 May 2017 Abstract In this paper, we
Seq2Tree: A Tree-Structured Extension of LSTM Network
Seq2Tree: A Tree-Structured Extension of LSTM Network Weicheng Ma Computer Science Department, Boston University 111 Cummington Mall, Boston, MA wcma@bu.edu Kai Cao Cambia Health Solutions kai.cao@cambiahealth.com
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
Chinese Character Handwriting Generation in TensorFlow
Chinese Character Handwriting Generation in TensorFlow Heri Zhao, Jiayu Ye, Ke Xu Abstract Recurrent neural network(rnn) has been proved to be successful in several sequence generation task. RNN can generate
arxiv: v2 [cs.sd] 7 Feb 2018
![arxiv: v2 [cs.sd] 7 Feb 2018](/thumbs/92/108747184.jpg "arxiv: v2 [cs.sd] 7 Feb 2018")
AUDIO SET CLASSIFICATION WITH ATTENTION MODEL: A PROBABILISTIC PERSPECTIVE Qiuqiang ong*, Yong Xu*, Wenwu Wang, Mark D. Plumbley Center for Vision, Speech and Signal Processing, University of Surrey, U
arxiv: v3 [stat.ml] 25 May 2016
![arxiv: v3 [stat.ml] 25 May 2016](/thumbs/79/80292488.jpg "arxiv: v3 [stat.ml] 25 May 2016")
A Theoretically Grounded Application of Dropout in Recurrent Neural Networks arxiv:1512.05287v3 [stat.ml] 25 May 2016 Yarin Gal University of Cambridge yg279@cam.ac.uk Abstract Recurrent neural networks
Deep Learning for Natural Language Processing. Sidharth Mudgal April 4, 2017
Deep Learning for Natural Language Processing Sidharth Mudgal April 4, 2017 Table of contents 1. Intro 2. Word Vectors 3. Word2Vec 4. Char Level Word Embeddings 5. Application: Entity Matching 6. Conclusion
arxiv: v5 [stat.ml] 5 Oct 2016
![arxiv: v5 [stat.ml] 5 Oct 2016](/thumbs/76/73771482.jpg "arxiv: v5 [stat.ml] 5 Oct 2016")
A Theoretically Grounded Application of Dropout in Recurrent Neural Networks Yarin Gal University of Cambridge {yg279,zg201}@cam.ac.uk Zoubin Ghahramani arxiv:1512.05287v5 [stat.ml] 5 Oct 2016 Abstract
CSC321 Lecture 10 Training RNNs
CSC321 Lecture 10 Training RNNs Roger Grosse and Nitish Srivastava February 23, 2015 Roger Grosse and Nitish Srivastava CSC321 Lecture 10 Training RNNs February 23, 2015 1 / 18 Overview Last time, we saw
arxiv: v2 [cs.sd] 18 Apr 2018
![arxiv: v2 [cs.sd] 18 Apr 2018](/thumbs/89/97991849.jpg "arxiv: v2 [cs.sd] 18 Apr 2018")
TASNET: TIME-DOMAIN AUDIO SEPARATION NETWORK FOR REAL-TIME, SINGLE-CHANNEL SPEECH SEPARATION Yi Luo Nima Mesgarani Department of Electrical Engineering, Columbia University, New York, NY arxiv:1711.00541v2
Spatial Transformer Networks
BIL722 - Deep Learning for Computer Vision Spatial Transformer Networks Max Jaderberg Andrew Zisserman Karen Simonyan Koray Kavukcuoglu Contents Introduction to Spatial Transformers Related Works Spatial
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
Classification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses about the label (Top-5 error) No Bounding Box
ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton Motivation Classification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses
AUDIO SET CLASSIFICATION WITH ATTENTION MODEL: A PROBABILISTIC PERSPECTIVE. Qiuqiang Kong*, Yong Xu*, Wenwu Wang, Mark D. Plumbley
AUDIO SET CLASSIFICATION WITH ATTENTION MODEL: A PROBABILISTIC PERSPECTIVE Qiuqiang ong*, Yong Xu*, Wenwu Wang, Mark D. Plumbley Center for Vision, Speech and Signal Processing, University of Surrey, U
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
arxiv: v3 [cs.cl] 1 Nov 2018
![arxiv: v3 [cs.cl] 1 Nov 2018](/thumbs/93/114210403.jpg "arxiv: v3 [cs.cl] 1 Nov 2018")
Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction Maha Elbayad 1,2 Laurent Besacier 1 Jakob Verbeek 2 Univ. Grenoble Alpes, CNRS, Grenoble INP, Inria, LIG, LJK,
A Neural Parametric Singing Synthesizer
INTERSPEECH 17 August 4, 17, Stockholm, Sweden A Neural Parametric Singing Synthesizer Merlijn Blaauw, Jordi Bonada Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain merlijn.blaauw@up.edu,
Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model
Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model Xingjian Shi 1 Zhihan Gao 1 Leonard Lausen 1 Hao Wang 1 Dit-Yan Yeung 1 Wai-kin Wong 2 Wang-chun Woo 2 1 Department of Computer Science
VAE with a VampPrior. Abstract. 1 Introduction
Jakub M. Tomczak University of Amsterdam Max Welling University of Amsterdam Abstract Many different methods to train deep generative models have been introduced in the past. In this paper, we propose
Tracking the World State with Recurrent Entity Networks
Tracking the World State with Recurrent Entity Networks Mikael Henaff, Jason Weston, Arthur Szlam, Antoine Bordes, Yann LeCun Task At each timestep, get information (in the form of a sentence) about the
arxiv: v3 [cs.lg] 20 Feb 2018
![arxiv: v3 [cs.lg] 20 Feb 2018](/thumbs/89/97777781.jpg "arxiv: v3 [cs.lg] 20 Feb 2018")
Or Sharir The Hebrew University of Jerusalem or.sharir@cs.huji.ac.il Amnon Shashua The Hebrew University of Jerusalem shashua@cs.huji.ac.il arxiv:1710.04404v [cs.lg] 20 Feb 2018 Abstract We present a novel
PREDICTION OF HETERODIMERIC PROTEIN COMPLEXES FROM PROTEIN-PROTEIN INTERACTION NETWORKS USING DEEP LEARNING
PREDICTION OF HETERODIMERIC PROTEIN COMPLEXES FROM PROTEIN-PROTEIN INTERACTION NETWORKS USING DEEP LEARNING Peiying (Colleen) Ruan, PhD, Deep Learning Solution Architect 3/26/2018 Background OUTLINE Method
Sylvester Normalizing Flows for Variational Inference
Sylvester Normalizing Flows for Variational Inference Rianne van den Berg Informatics Institute University of Amsterdam Leonard Hasenclever Department of statistics University of Oxford Jakub M. Tomczak
arxiv: v2 [cs.cv] 3 Jul 2018
![arxiv: v2 [cs.cv] 3 Jul 2018](/thumbs/81/83834217.jpg "arxiv: v2 [cs.cv] 3 Jul 2018")
Diversity encouraged learning of unsupervised LSTM ensemble for neural activity video prediction Yilin Song 1, Jonathan Viventi 2, and Yao Wang 1 1 Department of Electrical and Computer Engineering, New
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
Highway-LSTM and Recurrent Highway Networks for Speech Recognition
Highway-LSTM and Recurrent Highway Networks for Speech Recognition Golan Pundak, Tara N. Sainath Google Inc., New York, NY, USA {golan, tsainath}@google.com Abstract Recently, very deep networks, with
arxiv: v1 [cs.cl] 30 Oct 2018
![arxiv: v1 [cs.cl] 30 Oct 2018](/thumbs/94/120580009.jpg "arxiv: v1 [cs.cl] 30 Oct 2018")
Journal of Computer Science and Cybernetics, V.xx, N.x (20xx), 1 DOI no. 10.15625/1813-9663/xx/x/xxxx NEURAL MACHINE TRANSLATION BETWEEN VIETNAMESE AND ENGLISH: AN EMPIRICAL STUDY Hong-Hai Phan-Vu 1, Viet-Trung
arxiv: v2 [cs.cv] 19 Sep 2017
![arxiv: v2 [cs.cv] 19 Sep 2017](/thumbs/92/108885854.jpg "arxiv: v2 [cs.cv] 19 Sep 2017")
Learning Convolutional Networks for Content-weighted Image Compression arxiv:1703.10553v2 [cs.cv] 19 Sep 2017 Mu Li Hong Kong Polytechnic University csmuli@comp.polyu.edu.hk Shuhang Gu Hong Kong Polytechnic