Learning Long-Term Dependencies with Gradient Descent is Difficult
|
|
- Felix Malone
- 5 years ago
- Views:
Transcription
1 Learning Long-Term Dependencies with Gradient Descent is Difficult Y. Bengio, P. Simard & P. Frasconi, IEEE Trans. Neural Nets, 1994 June 23, 2016, ICML, New York City Back-to-the-future Workshop Yoshua Bengio Montreal InsDtute for Learning Algorithms Université de Montréal
2 Simple Experiments from 1992 while I was at MIT 2 categories of sequences Can the single tanh unit learn to store for T Hme steps 1 bit of informahon given by the sign of inihal input? Prob(success seq. length T) 2
3 How to store 1 bit? Dynamics with multiple basins of attraction in some dimensions Some subspace of the state can store 1 or more bits of informahon if the dynamical system has mulhple basins of aqrachon in some dimensions Basins boundary Bit=0 Bit=1 3
4 Robustly storing 1 bit in the presence of bounded noise With spectral radius > 1, noise can kick state out of aqractor M >1 β Γ M <1 X UNSTABLE Domain of a t β Not so with radius<1 CONTRACTIVE à STABLE M >1 Γ X M <1 4 Domain of a t
5 Storing Reliably è Vanishing gradients Reliably storing bits of informahon requires spectral radius<1 The product of T matrices whose spectral radius is < 1 is a matrix whose spectral radius converges to 0 at exponenhal rate in T If spectral radius of Jacobian is < 1 è propagated gradients vanish 5
6 Vanishing or Exploding Gradients Hochreiter s 1991 MSc thesis (in German) had independently discovered that backpropagated gradients in RNNs tend to either vanish or explode as sequence length increases 6
7 Why it hurts gradient-based learning Long-term dependencies get a weight that is exponenhally smaller (in T) compared to short-term dependencies Becomes exponenhally smaller for longer Hme differences, when spectral radius < 1 7
8 Dealing with Gradient Explosion by Gradient Norm Clipping (Mikolov thesis 2012; Pascanu, Mikolov, Bengio, ICML 2013) 8 error
9 Conference version (1993) of the 1994 paper by the same authors had a predecessor of GRU and targetprop (The problem of learning long-term dependencies in recurrent networks, Bengio, Frasconi & Simard ICNN 1993) Flip-flop unit to store 1 bit, with gahng signal to control when to write Pseudo-backprop through it by a form of targetprop 9
10 Bypassing nonlinearities to learn longer term dependencies Delays (Lin et al & Giles 1995) MulHple Hme scales (Elhihi & Bengio NIPS 1995) s o x W 1 W 3 o t 1 o t o t+1 W 3 W 3 W 3 s t 2 s t 1 s t s t+1 W 1 W 1 W 1 W 1 W 3 unfold x t 1 x t x t+1 10
11 Fighting the vanishing gradient: LSTM & GRU Create a path where gradients can flow for longer with a self-loop Corresponds to an eigenvalue of Jacobian slightly less than 1 LSTM is now heavily used (Hochreiter & Schmidhuber 1997) GRU light-weight version (Cho et al 2014) 11 (Hochreiter 1991); first version of the LSTM, called Neural Long- Term Storage with self-loop LSTM: (Hochreiter & Schmidhuber 1997) output self-loop + state input input gate forget gate output gate
12 Fast Forward 20 years: Attention Mechanisms for Memory Access Neural Turing Machines (Graves et al 2014) and Memory Networks (Weston et al 2014) Use a content-based aqenhon mechanism (Bahdanau et al 2014) to control the read and write access into a memory The aqenhon mechanism outputs a soimax over memory locahons write read 12
13 Large Memory Networks: Sparse Access Memory for Long-Term Dependencies A mental state stored in an external memory can stay for arbitrarily long durahons, unhl it is overwriqen (parhally or not) Forgekng = vanishing gradient. Memory = higher-dimensional state, avoiding or reducing the need for forgekng/vanishing passive copy access 13
14 Designing the RNN Architecture (Zhang et al 2016) Recurrent depth: max path length divided by sequence length Feedforward depth: max length from input to nearest output Skip coefficient: shortest path length divided sequence length 14
15 (a) (a) (3) (4) (b) Figure 2: Left: (a) the architectures for sh, st, bu and td, with their (d r,d f ) equal to (1, 2), (1, 3), (1, 3) and (2, 3), respectively. The longest path in td are colored in red. (b) The 9 architectures denoted by their (d f,d r ) with d r =1, 2, 3 and d f =2, 3, 4. We only plot the hidden states within 1 time step (which also have a period of It 1) in both makes (a) and (b). Right: a (a) Various difference architectures that we consider in Section 4.4. From top to bottom are baseline s =1, and s =2, s =3. (b) Proposed architectures that we consider in Section 4.5 where we take k =3as an example. The shortest paths in (a) and (b) that correspond to the recurrent skip coefficients are colored in blue. Impact of change in recurrent depth DATASET MODELS\ARCHS sh st bu td PennTreebank tanh RNN tanh RNN-SMALL text8 tanh RNN-LARGE LSTM-SMALL LSTM-LARGE Impact of change in skip coefficient sequential MNIST 34.9 dataset: 46.9 Each 74.9 MNIST image data MNIST is reshaped into a sequence, 84.8 turning the digit classification s=1task s=3 into Figure s=5 a sequence s=7 2: Left: s=9 classification (a) the architectures one s=1 with s=3 long-term for sh, s=4st, dependencies s=5 bu s=6 and td, with [25, 24]. their (d r,d f pmnist (2, ), respectively The pmnist longest 28.5 path25.0 in td colored 65.9 A slight modification of the dataset is to permute the image sequences are by abaseline fixed random red. order (b) s The =1, 9 archa beforehand (permuted Model MNIST). withresults dpmnist r =1, in [25] 2, 3 and havedshown f =2, that 3, 4. both Wetanh only RNNs plot and the LSTMs hidden states did notwithin 1 t Architecture, s (1), 1 (2), of 1) in both (a) and (b). Right: (a) Various k 1 (3), achieve satisfying irnn[25] performance, 97.0 which 82.0 also highlights the difficulty of this task. architectures =3as that anwexampl k (4), k 2 consider i MNIST k = urnn[24] 95.1 are baseline 91.4 For all of our experiments we use Adam s [26] =1, for and optimization, s k =2, = 21 s 39.5 =3. and (b) 39.9 conduct Proposed 69.6 architectures that we con k =3as an example. The shortest paths colored a grid 71.8 LSTM[24] search in (a) and (b) inthat blue. on the learningrnn(tanh)[25] rate {10 2, , , 10 5 pmnist k = }. For tanh RNNs, the parameters are initializedcorrespond with to samples from a uniform distribution. colored infor blue. k= stanh(s = 21, 11) LSTM networks we adopt a similar initialization scheme, while the forget gate biases are chosen by the grid search on { 5, 3, 1, 0, 1, 3, 5}. We employ Table 2: Results for MNIST/pMNIST. Top-left: test accuracies with different s for tanh RNN. Top-right: test early stopping and the batch size was DATASET set to 50. MODELS\ARCHS sh DATASET st bu td accuracies with different s for LSTM. Bottom: compared to previous results. Bottom-right: test accuracies for architectures (1), (2), (3) and (4) for tanh PennTreebank RNN. tanh RNN d Recurrent Depth is Non-trivial tanh RNN-SMALL 1.80 PennTreebank d f Table 2, bottom-left panel, shows that our text8 simple architecture tanh RNN-LARGE improves upon the urnn 1.69 by % 1.64 on 1.59 d f TopMNIST, investigate and the achieves first almost question, the same we compare performance 4 similar as LSTM LSTM-SMALL connecting the MNIST architectures: dataset 1.65 with 1-layer 1.66 only 25% 1.65 (shallow) 1.63 d f sh, number 2-layers of parameters stacked st, [24]. 2-layers Note thatstacked obtainingwith goodanperformance extra bottom-up on sequential connection MNIST bu, requires and 2-layers a (a) (a) d f \d r d r =1 d r =2 d r =3 d f = d f = d f = Figure 2: Left: (a) (2, 3), respectively. with d r =1, 2, 3 an of 1) in both (a) and Table 1: Left: test BPCs of sh, st, bu, td for tanh RNNs and LSTMs. Right: test BPCs of tanh RNNs with recurrent depth d r =1, 2, 3 and feedforward depth d f =2, 3, 4 respectively. RNN(tanh) s = 1 s = 5 s = 9 s = 13 s = 21 LSTM s=1 s=3 s=5 s=7 s=9 ( (
16 New Ideas to Help Information Propagation Unitary matrices: all e-values of matrix are 1 (Arjowski, Amar & Bengio ICML 2016) Zoneout: randomly choose to simply copy the state unchanged (Krueger et al 2016, submiyed) 16
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
More informationRecurrent Neural Networks. Jian Tang
Recurrent Neural Networks Jian Tang tangjianpku@gmail.com 1 RNN: Recurrent neural networks Neural networks for sequence modeling Summarize a sequence with fix-sized vector through recursively updating
More informationSlide credit from Hung-Yi Lee & Richard Socher
Slide credit from Hung-Yi Lee & Richard Socher 1 Review Recurrent Neural Network 2 Recurrent Neural Network Idea: condition the neural network on all previous words and tie the weights at each time step
More informationLecture 11 Recurrent Neural Networks I
Lecture 11 Recurrent Neural Networks I CMSC 35246: Deep Learning Shubhendu Trivedi & Risi Kondor University of Chicago May 01, 2017 Introduction Sequence Learning with Neural Networks Some Sequence Tasks
More informationLecture 11 Recurrent Neural Networks I
Lecture 11 Recurrent Neural Networks I CMSC 35246: Deep Learning Shubhendu Trivedi & Risi Kondor niversity of Chicago May 01, 2017 Introduction Sequence Learning with Neural Networks Some Sequence Tasks
More informationEE-559 Deep learning LSTM and GRU
EE-559 Deep learning 11.2. LSTM and GRU François Fleuret https://fleuret.org/ee559/ Mon Feb 18 13:33:24 UTC 2019 ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNE The Long-Short Term Memory unit (LSTM) by Hochreiter
More informationRecurrent 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,
More informationRecurrent Neural Networks (Part - 2) Sumit Chopra Facebook
Recurrent Neural Networks (Part - 2) Sumit Chopra Facebook Recap Standard RNNs Training: Backpropagation Through Time (BPTT) Application to sequence modeling Language modeling Applications: Automatic speech
More informationNeural 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
More informationAnalysis of the Learning Process of a Recurrent Neural Network on the Last k-bit Parity Function
Analysis of the Learning Process of a Recurrent Neural Network on the Last k-bit Parity Function Austin Wang Adviser: Xiuyuan Cheng May 4, 2017 1 Abstract This study analyzes how simple recurrent neural
More informationIntroduction to RNNs!
Introduction to RNNs Arun Mallya Best viewed with Computer Modern fonts installed Outline Why Recurrent Neural Networks (RNNs)? The Vanilla RNN unit The RNN forward pass Backpropagation refresher The RNN
More informationarxiv: v3 [cs.lg] 12 Nov 2016
Architectural Complexity Measures of Recurrent Neural Networks arxiv:162.821v3 [cs.lg] 12 Nov 216 Saizheng Zhang 1,, Yuhuai Wu 2,, Tong Che 4, Zhouhan Lin 1, Roland Memisevic 1,5, Ruslan Salakhutdinov
More informationCSC321 Lecture 15: Exploding and Vanishing Gradients
CSC321 Lecture 15: Exploding and Vanishing Gradients Roger Grosse Roger Grosse CSC321 Lecture 15: Exploding and Vanishing Gradients 1 / 23 Overview Yesterday, we saw how to compute the gradient descent
More informationLong-Short Term Memory and Other Gated RNNs
Long-Short Term Memory and Other Gated RNNs Sargur Srihari srihari@buffalo.edu This is part of lecture slides on Deep Learning: http://www.cedar.buffalo.edu/~srihari/cse676 1 Topics in Sequence Modeling
More informationLecture 15: Exploding and Vanishing Gradients
Lecture 15: Exploding and Vanishing Gradients Roger Grosse 1 Introduction Last lecture, we introduced RNNs and saw how to derive the gradients using backprop through time. In principle, this lets us train
More informationRecurrent Neural Network Training with Preconditioned Stochastic Gradient Descent
Recurrent Neural Network Training with Preconditioned Stochastic Gradient Descent 1 Xi-Lin Li, lixilinx@gmail.com arxiv:1606.04449v2 [stat.ml] 8 Dec 2016 Abstract This paper studies the performance of
More informationLong-Short Term Memory
Long-Short Term Memory Sepp Hochreiter, Jürgen Schmidhuber Presented by Derek Jones Table of Contents 1. Introduction 2. Previous Work 3. Issues in Learning Long-Term Dependencies 4. Constant Error Flow
More informationFaster Training of Very Deep Networks Via p-norm Gates
Faster Training of Very Deep Networks Via p-norm Gates Trang Pham, Truyen Tran, Dinh Phung, Svetha Venkatesh Center for Pattern Recognition and Data Analytics Deakin University, Geelong Australia Email:
More informationGated Recurrent Neural Tensor Network
Gated Recurrent Neural Tensor Network Andros Tjandra, Sakriani Sakti, Ruli Manurung, Mirna Adriani and Satoshi Nakamura Faculty of Computer Science, Universitas Indonesia, Indonesia Email: andros.tjandra@gmail.com,
More informationNeural Networks Language Models
Neural Networks Language Models Philipp Koehn 10 October 2017 N-Gram Backoff Language Model 1 Previously, we approximated... by applying the chain rule p(w ) = p(w 1, w 2,..., w n ) p(w ) = i p(w i w 1,...,
More informationarxiv: v3 [cs.lg] 14 Jan 2018
A Gentle Tutorial of Recurrent Neural Network with Error Backpropagation Gang Chen Department of Computer Science and Engineering, SUNY at Buffalo arxiv:1610.02583v3 [cs.lg] 14 Jan 2018 1 abstract We describe
More informationRecurrent 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
More informationRECURRENT NEURAL NETWORKS WITH FLEXIBLE GATES USING KERNEL ACTIVATION FUNCTIONS
2018 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, SEPT. 17 20, 2018, AALBORG, DENMARK RECURRENT NEURAL NETWORKS WITH FLEXIBLE GATES USING KERNEL ACTIVATION FUNCTIONS Simone Scardapane,
More informationEE-559 Deep learning Recurrent Neural Networks
EE-559 Deep learning 11.1. Recurrent Neural Networks François Fleuret https://fleuret.org/ee559/ Sun Feb 24 20:33:31 UTC 2019 Inference from sequences François Fleuret EE-559 Deep learning / 11.1. Recurrent
More informationCSC321 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
More informationRECURRENT NETWORKS I. Philipp Krähenbühl
RECURRENT NETWORKS I Philipp Krähenbühl RECAP: CLASSIFICATION conv 1 conv 2 conv 3 conv 4 1 2 tu RECAP: SEGMENTATION conv 1 conv 2 conv 3 conv 4 RECAP: DETECTION conv 1 conv 2 conv 3 conv 4 RECAP: GENERATION
More informationLong Short- Term Memory (LSTM) M1 Yuichiro Sawai Computa;onal Linguis;cs Lab. January 15, Deep Lunch
Long Short- Term Memory (LSTM) M1 Yuichiro Sawai Computa;onal Linguis;cs Lab. January 15, 2015 @ Deep Lunch 1 Why LSTM? OJen used in many recent RNN- based systems Machine transla;on Program execu;on Can
More informationLearning Long Term Dependencies with Gradient Descent is Difficult
Learning Long Term Dependencies with Gradient Descent is Difficult IEEE Trans. on Neural Networks 1994 Yoshua Bengio, Patrice Simard, Paolo Frasconi Presented by: Matt Grimes, Ayse Naz Erkan Recurrent
More informationModelling Time Series with Neural Networks. Volker Tresp Summer 2017
Modelling Time Series with Neural Networks Volker Tresp Summer 2017 1 Modelling of Time Series The next figure shows a time series (DAX) Other interesting time-series: energy prize, energy consumption,
More informationarxiv: v2 [cs.lg] 29 Feb 2016
arxiv:162.821v2 [cs.lg] 29 Feb 216 Saizheng Zhang 1, SAIZHENG.ZHANG@UMONTREAL.CA Yuhuai Wu 2, YWU@CS.TORONTO.EDU Tong Che 3 TONGCHE@IHES.FR Zhouhan Lin 1 LIN.ZHOUHAN@GMAIL.COM Roland Memisevic 1,5 ROLAND.UMONTREAL@GMAIL.COM
More informationarxiv: v5 [cs.lg] 28 Feb 2017
RECURRENT BATCH NORMALIZATION Tim Cooijmans, Nicolas Ballas, César Laurent, Çağlar Gülçehre & Aaron Courville MILA - Université de Montréal firstname.lastname@umontreal.ca ABSTRACT arxiv:1603.09025v5 [cs.lg]
More informationLearning Unitary Operators with Help from u(n)
@_hylandsl Learning Unitary Operators with Help from u(n) Stephanie L. Hyland 1,2, Gunnar Rätsch 1 1 Department of Computer Science, ETH Zurich 2 Tri-Institutional Training Program in Computational Biology
More informationCOMPARING FIXED AND ADAPTIVE COMPUTATION TIME FOR RE-
Workshop track - ICLR COMPARING FIXED AND ADAPTIVE COMPUTATION TIME FOR RE- CURRENT NEURAL NETWORKS Daniel Fojo, Víctor Campos, Xavier Giró-i-Nieto Universitat Politècnica de Catalunya, Barcelona Supercomputing
More informationMULTIPLICATIVE 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
More informationDeep Learning Recurrent Networks 2/28/2018
Deep Learning Recurrent Networks /8/8 Recap: Recurrent networks can be incredibly effective Story so far Y(t+) Stock vector X(t) X(t+) X(t+) X(t+) X(t+) X(t+5) X(t+) X(t+7) Iterated structures are good
More informationBased on the original slides of Hung-yi Lee
Based on the original slides of Hung-yi Lee New Activation Function Rectified Linear Unit (ReLU) σ z a a = z Reason: 1. Fast to compute 2. Biological reason a = 0 [Xavier Glorot, AISTATS 11] [Andrew L.
More informationConvolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting 卷积 LSTM 网络 : 利用机器学习预测短期降雨 施行健 香港科技大学 VALSE 2016/03/23
Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting 卷积 LSTM 网络 : 利用机器学习预测短期降雨 施行健 香港科技大学 VALSE 2016/03/23 Content Quick Review of Recurrent Neural Network Introduction
More informationDirect Method for Training Feed-forward Neural Networks using Batch Extended Kalman Filter for Multi- Step-Ahead Predictions
Direct Method for Training Feed-forward Neural Networks using Batch Extended Kalman Filter for Multi- Step-Ahead Predictions Artem Chernodub, Institute of Mathematical Machines and Systems NASU, Neurotechnologies
More informationarxiv: v2 [cs.ne] 7 Apr 2015
A Simple Way to Initialize Recurrent Networks of Rectified Linear Units arxiv:154.941v2 [cs.ne] 7 Apr 215 Quoc V. Le, Navdeep Jaitly, Geoffrey E. Hinton Google Abstract Learning long term dependencies
More informationarxiv: v3 [cs.lg] 25 Oct 2017
Gated Orthogonal Recurrent Units: On Learning to Forget Li Jing 1, Caglar Gulcehre 2, John Peurifoy 1, Yichen Shen 1, Max Tegmark 1, Marin Soljačić 1, Yoshua Bengio 2 1 Massachusetts Institute of Technology,
More informationRecurrent Neural Networks 2. CS 287 (Based on Yoav Goldberg s notes)
Recurrent Neural Networks 2 CS 287 (Based on Yoav Goldberg s notes) Review: Representation of Sequence Many tasks in NLP involve sequences w 1,..., w n Representations as matrix dense vectors X (Following
More informationRecurrent and Recursive Networks
Neural Networks with Applications to Vision and Language Recurrent and Recursive Networks Marco Kuhlmann Introduction Applications of sequence modelling Map unsegmented connected handwriting to strings.
More informationRecurrent Neural Networks
Recurrent Neural Networks Datamining Seminar Kaspar Märtens Karl-Oskar Masing Today's Topics Modeling sequences: a brief overview Training RNNs with back propagation A toy example of training an RNN Why
More informationarxiv: 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
More informationHigh 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
More informationStephen Scott.
1 / 35 (Adapted from Vinod Variyam and Ian Goodfellow) sscott@cse.unl.edu 2 / 35 All our architectures so far work on fixed-sized inputs neural networks work on sequences of inputs E.g., text, biological
More informationRecurrent 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
More informationRecurrent neural networks
12-1: Recurrent neural networks Prof. J.C. Kao, UCLA Recurrent neural networks Motivation Network unrollwing Backpropagation through time Vanishing and exploding gradients LSTMs GRUs 12-2: Recurrent neural
More informationarxiv: v4 [cs.lg] 25 May 2016
arxiv:1511.06464v4 [cs.lg] 25 May 2016 Martin Arjovsky Amar Shah Yoshua Bengio Universidad de Buenos Aires, University of Cambridge, Université de Montréal. Yoshua Bengio is a CIFAR Senior Fellow. Indicates
More informationNatural Language Processing and Recurrent Neural Networks
Natural Language Processing and Recurrent Neural Networks Pranay Tarafdar October 19 th, 2018 Outline Introduction to NLP Word2vec RNN GRU LSTM Demo What is NLP? Natural Language? : Huge amount of information
More informationLearning Recurrent Neural Networks with Hessian-Free Optimization: Supplementary Materials
Learning Recurrent Neural Networks with Hessian-Free Optimization: Supplementary Materials Contents 1 Pseudo-code for the damped Gauss-Newton vector product 2 2 Details of the pathological synthetic problems
More informationarxiv: v1 [stat.ml] 31 Oct 2016
Full-Capacity Unitary Recurrent Neural Networks arxiv:1611.00035v1 [stat.ml] 31 Oct 2016 Scott Wisdom 1, Thomas Powers 1, John R. Hershey 2, Jonathan Le Roux 2, and Les Atlas 1 1 Department of Electrical
More informationDeep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, Spis treści
Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, 2017 Spis treści Website Acknowledgments Notation xiii xv xix 1 Introduction 1 1.1 Who Should Read This Book?
More informationTTIC 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
More informationCombining Static and Dynamic Information for Clinical Event Prediction
Combining Static and Dynamic Information for Clinical Event Prediction Cristóbal Esteban 1, Antonio Artés 2, Yinchong Yang 1, Oliver Staeck 3, Enrique Baca-García 4 and Volker Tresp 1 1 Siemens AG and
More informationLecture 5: Recurrent Neural Networks
1/25 Lecture 5: Recurrent Neural Networks Nima Mohajerin University of Waterloo WAVE Lab nima.mohajerin@uwaterloo.ca July 4, 2017 2/25 Overview 1 Recap 2 RNN Architectures for Learning Long Term Dependencies
More informationDeep Recurrent Neural Networks
Deep Recurrent Neural Networks Artem Chernodub e-mail: a.chernodub@gmail.com web: http://zzphoto.me ZZ Photo IMMSP NASU 2 / 28 Neuroscience Biological-inspired models Machine Learning p x y = p y x p(x)/p(y)
More informationarxiv: v1 [stat.ml] 29 Jul 2017
ORHOGONAL RECURREN NEURAL NEWORKS WIH SCALED CAYLEY RANSFORM Kyle E. Helfrich, Devin Willmott, & Qiang Ye Department of Mathematics University of Kentucky Lexington, KY 40506, USA {kyle.helfrich,devin.willmott,qye3}@uky.edu
More informationImproved Learning through Augmenting the Loss
Improved Learning through Augmenting the Loss Hakan Inan inanh@stanford.edu Khashayar Khosravi khosravi@stanford.edu Abstract We present two improvements to the well-known Recurrent Neural Network Language
More informationarxiv: v3 [stat.ml] 19 Jun 2018
arxiv:1707.09520v3 [stat.ml] 19 Jun 2018 Kyle E. Helfrich * 1 Devin Willmott * 1 Qiang Ye 1 Abstract Recurrent Neural Networks (RNNs) are designed to handle sequential data but suffer from vanishing or
More informationDeep 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
More informationRecurrent Neural Networks. deeplearning.ai. Why sequence models?
Recurrent Neural Networks deeplearning.ai Why sequence models? Examples of sequence data The quick brown fox jumped over the lazy dog. Speech recognition Music generation Sentiment classification There
More informationSequence Modeling with Neural Networks
Sequence Modeling with Neural Networks Harini Suresh y 0 y 1 y 2 s 0 s 1 s 2... x 0 x 1 x 2 hat is a sequence? This morning I took the dog for a walk. sentence medical signals speech waveform Successes
More informationCSC321 Lecture 16: ResNets and Attention
CSC321 Lecture 16: ResNets and Attention Roger Grosse Roger Grosse CSC321 Lecture 16: ResNets and Attention 1 / 24 Overview Two topics for today: Topic 1: Deep Residual Networks (ResNets) This is the state-of-the
More informationarxiv: 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
More informationDeep Gate Recurrent Neural Network
JMLR: Workshop and Conference Proceedings 63:350 365, 2016 ACML 2016 Deep Gate Recurrent Neural Network Yuan Gao University of Helsinki Dorota Glowacka University of Helsinki gaoyuankidult@gmail.com glowacka@cs.helsinki.fi
More informationNeural Networks 2. 2 Receptive fields and dealing with image inputs
CS 446 Machine Learning Fall 2016 Oct 04, 2016 Neural Networks 2 Professor: Dan Roth Scribe: C. Cheng, C. Cervantes Overview Convolutional Neural Networks Recurrent Neural Networks 1 Introduction There
More informationarxiv: v1 [cs.cl] 31 May 2015
Recurrent Neural Networks with External Memory for Language Understanding Baolin Peng 1, Kaisheng Yao 2 1 The Chinese University of Hong Kong 2 Microsoft Research blpeng@se.cuhk.edu.hk, kaisheny@microsoft.com
More informationIMPROVING PERFORMANCE OF RECURRENT NEURAL
IMPROVING PERFORMANCE OF RECURRENT NEURAL NETWORK WITH RELU NONLINEARITY Sachin S. Talathi & Aniket Vartak Qualcomm Research San Diego, CA 92121, USA {stalathi,avartak}@qti.qualcomm.com ABSTRACT In recent
More informationarxiv: v1 [cs.ne] 19 Dec 2016
A RECURRENT NEURAL NETWORK WITHOUT CHAOS Thomas Laurent Department of Mathematics Loyola Marymount University Los Angeles, CA 90045, USA tlaurent@lmu.edu James von Brecht Department of Mathematics California
More informationCSC321 Lecture 15: Recurrent Neural Networks
CSC321 Lecture 15: Recurrent Neural Networks Roger Grosse Roger Grosse CSC321 Lecture 15: Recurrent Neural Networks 1 / 26 Overview Sometimes we re interested in predicting sequences Speech-to-text and
More informationShort-term water demand forecast based on deep neural network ABSTRACT
Short-term water demand forecast based on deep neural network Guancheng Guo 1, Shuming Liu 2 1,2 School of Environment, Tsinghua University, 100084, Beijing, China 2 shumingliu@tsinghua.edu.cn ABSTRACT
More informationEfficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections
Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections Different methods have been suggested to solve either the vanishing or exploding gradient problem. The LSTM
More informationGenerating 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
More informationReservoir Computing and Echo State Networks
An Introduction to: Reservoir Computing and Echo State Networks Claudio Gallicchio gallicch@di.unipi.it Outline Focus: Supervised learning in domain of sequences Recurrent Neural networks for supervised
More informationLecture 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
More informationNeed for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels
Need for Deep Networks Perceptron Can only model linear functions Kernel Machines Non-linearity provided by kernels Need to design appropriate kernels (possibly selecting from a set, i.e. kernel learning)
More informationCAN RECURRENT NEURAL NETWORKS WARP TIME?
CAN RECURRENT NEURAL NETWORKS WARP TIME? Corentin Tallec Laboratoire de Recherche en Informatique Université Paris Sud Gif-sur-Yvette, 99, France corentin.tallec@u-psud.fr Yann Ollivier Facebook Artificial
More informationCredit Assignment: Beyond Backpropagation
Credit Assignment: Beyond Backpropagation Yoshua Bengio 11 December 2016 AutoDiff NIPS 2016 Workshop oo b s res P IT g, M e n i arn nlin Le ain o p ee em : D will r G PLU ters p cha k t, u o is Deep Learning
More informationarxiv: v1 [cs.lg] 2 Feb 2018
Short-term Memory of Deep RNN Claudio Gallicchio arxiv:1802.00748v1 [cs.lg] 2 Feb 2018 Department of Computer Science, University of Pisa Largo Bruno Pontecorvo 3-56127 Pisa, Italy Abstract. The extension
More informationCSCI 315: Artificial Intelligence through Deep Learning
CSCI 315: Artificial Intelligence through Deep Learning W&L Winter Term 2017 Prof. Levy Recurrent Neural Networks (Chapter 7) Recall our first-week discussion... How do we know stuff? (MIT Press 1996)
More informationNeed for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels
Need for Deep Networks Perceptron Can only model linear functions Kernel Machines Non-linearity provided by kernels Need to design appropriate kernels (possibly selecting from a set, i.e. kernel learning)
More informationConvolutional Neural Networks II. Slides from Dr. Vlad Morariu
Convolutional Neural Networks II Slides from Dr. Vlad Morariu 1 Optimization Example of optimization progress while training a neural network. (Loss over mini-batches goes down over time.) 2 Learning rate
More informationDemystifying deep learning. Artificial Intelligence Group Department of Computer Science and Technology, University of Cambridge, UK
Demystifying deep learning Petar Veličković Artificial Intelligence Group Department of Computer Science and Technology, University of Cambridge, UK London Data Science Summit 20 October 2017 Introduction
More informationLSTM CAN SOLVE HARD. Jurgen Schmidhuber Lugano, Switzerland. Abstract. guessing than by the proposed algorithms.
LSTM CAN SOLVE HARD LONG TIME LAG PROBLEMS Sepp Hochreiter Fakultat fur Informatik Technische Universitat Munchen 80290 Munchen, Germany Jurgen Schmidhuber IDSIA Corso Elvezia 36 6900 Lugano, Switzerland
More informationEquivalence Results between Feedforward and Recurrent Neural Networks for Sequences
Equivalence Results between Feedforward and Recurrent Neural Networks for Sequences Alessandro Sperduti Department of Mathematics University of Padova, Italy Email: sperduti@mathunipdit Abstract In the
More informationCSE 591: Introduction to Deep Learning in Visual Computing. - Parag S. Chandakkar - Instructors: Dr. Baoxin Li and Ragav Venkatesan
CSE 591: Introduction to Deep Learning in Visual Computing - Parag S. Chandakkar - Instructors: Dr. Baoxin Li and Ragav Venkatesan Overview Background Why another network structure? Vanishing and exploding
More informationCheng Soon Ong & Christian Walder. Canberra February June 2018
Cheng Soon Ong & Christian Walder Research Group and College of Engineering and Computer Science Canberra February June 2018 Outlines Overview Introduction Linear Algebra Probability Linear Regression
More informationRecurrent Neural Networks Deep Learning Lecture 5. Efstratios Gavves
Recurrent Neural Networks Deep Learning Lecture 5 Efstratios Gavves Sequential Data So far, all tasks assumed stationary data Neither all data, nor all tasks are stationary though Sequential Data: Text
More informationChristian Mohr
Christian Mohr 20.12.2011 Recurrent Networks Networks in which units may have connections to units in the same or preceding layers Also connections to the unit itself possible Already covered: Hopfield
More informationDeep Learning Made Easier by Linear Transformations in Perceptrons
Deep Learning Made Easier by Linear Transformations in Perceptrons Tapani Raiko Aalto University School of Science Dept. of Information and Computer Science Espoo, Finland firstname.lastname@aalto.fi Harri
More informationDeep Learning Recurrent Networks 10/11/2017
Deep Learning Recurrent Networks 10/11/2017 1 Which open source project? Related math. What is it talking about? And a Wikipedia page explaining it all The unreasonable effectiveness of recurrent neural
More informationArtificial Neural Networks D B M G. Data Base and Data Mining Group of Politecnico di Torino. Elena Baralis. Politecnico di Torino
Artificial Neural Networks Data Base and Data Mining Group of Politecnico di Torino Elena Baralis Politecnico di Torino Artificial Neural Networks Inspired to the structure of the human brain Neurons as
More informationGated Feedback Recurrent Neural Networks
Junyoung Chung Caglar Gulcehre Kyunghyun Cho Yoshua Bengio Dept. IRO, Université de Montréal, CIFAR Senior Fellow JUNYOUNG.CHUNG@UMONTREAL.CA CAGLAR.GULCEHRE@UMONTREAL.CA KYUNGHYUN.CHO@UMONTREAL.CA FIND-ME@THE.WEB
More informationJakub Hajic Artificial Intelligence Seminar I
Jakub Hajic Artificial Intelligence Seminar I. 11. 11. 2014 Outline Key concepts Deep Belief Networks Convolutional Neural Networks A couple of questions Convolution Perceptron Feedforward Neural Network
More informationMachine Learning for Large-Scale Data Analysis and Decision Making A. Neural Networks Week #6
Machine Learning for Large-Scale Data Analysis and Decision Making 80-629-17A Neural Networks Week #6 Today Neural Networks A. Modeling B. Fitting C. Deep neural networks Today s material is (adapted)
More informationIndex. Santanu Pattanayak 2017 S. Pattanayak, Pro Deep Learning with TensorFlow,
Index A Activation functions, neuron/perceptron binary threshold activation function, 102 103 linear activation function, 102 rectified linear unit, 106 sigmoid activation function, 103 104 SoftMax activation
More informationConvolutional Neural Network Architecture
Convolutional Neural Network Architecture Zhisheng Zhong Feburary 2nd, 2018 Zhisheng Zhong Convolutional Neural Network Architecture Feburary 2nd, 2018 1 / 55 Outline 1 Introduction of Convolution Motivation
More informationOn the use of Long-Short Term Memory neural networks for time series prediction
On the use of Long-Short Term Memory neural networks for time series prediction Pilar Gómez-Gil National Institute of Astrophysics, Optics and Electronics ccc.inaoep.mx/~pgomez In collaboration with: J.
More informationMachine 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
More information