lecture 9 recurrent neural networks
play

Lecture 9 Recurrent Neural Networks Im glad that Im Turing Complete - PowerPoint PPT Presentation

Jan 05, 2023 •30 likes •1.48k views

Lecture 9 Recurrent Neural Networks Im glad that Im 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 lot to cover and DONT

  1. https://distill.pub/2016/augmented-rnns

  2. https://distill.pub/2016/augmented-rnns

  3. https://distill.pub/2016/augmented-rnns

  4. https://distill.pub/2016/augmented-rnns

  5. https://distill.pub/2016/augmented-rnns

  6. Image Attention: Image Captioning ● Xu, Kelvin, et al. "Show, attend and tell: Neural image caption generation with visual attention." International Conference on Machine Learning. 2015.

  15. Image Attention: Image Captioning

  16. Image Attention: Image Captioning

  17. Text Recognition ● Implicit language model

  18. Text Recognition ● Implicit language model

  19. Soft Attention RNN for OCR Loss 2 金口香牛肉面 金 口 Attention CNN Column FC 金口香牛肉面 Loss 1

  20. RNN with External Memory

  21. Copy a sequence Input Output

  22. Copy a sequence Input Solution in Python Output

  23. Copy a sequence Can neural network Input learn this program Solution in Python purely from data? Output

  24. Traditional Machine Learning ● √ Elementary Operations ● √* Logic flow control ○ Decision tree ● × External Memory ○ As opposed to internal memory (hidden states) Graves, Alex, Greg Wayne, and Ivo Danihelka. "Neural turing machines." arXiv preprint arXiv:1410.5401 (2014).

  25. Traditional Machine Learning ● √ Elementary Operations ● √* Logic flow control ● × External Memory Graves, Alex, Greg Wayne, and Ivo Danihelka. "Neural turing machines." arXiv preprint arXiv:1410.5401 (2014).

  26. Neural Turing Machines (NTM) ● NTM is a neural networks with a working memory ● It reads and write multiple times at each step ● Fully differentiable and can be trained end-to-end An NTM “Cell” Graves, Alex, Greg Wayne, and Ivo Danihelka. "Neural turing machines." arXiv preprint arXiv:1410.5401 (2014).

  27. Neural Turing Machines (NTM) m ● Memory ○ Sdfsdf n http://llcao.net/cu-deeplearning15/presentation/NeuralTuringMachines.pdf

  28. Neural Turing Machines (NTM) ● Read ● Hard indexing ⇒ Soft Indexing ○ A distribution of index ○ “Attention”

  29. Neural Turing Machines (NTM) ● Read Memory Locations ● Hard indexing ⇒ Soft Indexing ○ A distribution of index ○ “Attention”

  30. Neural Turing Machines (NTM) ● Read Memory Locations ● Hard indexing ⇒ Soft Indexing ○ A distribution of index ○ “Attention”

  31. Neural Turing Machines (NTM) ● Write ○ Write = erase + add erase add

  32. Neural Turing Machines (NTM) ● Write ○ Write = erase + add erase add

  33. Neural Turing Machines (NTM) ● Addressing

  34. Neural Turing Machines (NTM) ● Addressing ● 1. Focusing by Content ● Cosine Similarity

  35. Neural Turing Machines (NTM) ● Addressing ● 1. Focusing by Content ● Cosine Similarity

  36. Neural Turing Machines (NTM) ● 1. Focusing by Content ● 2. Interpolate with previous step

  37. Neural Turing Machines (NTM) ● 1. Focusing by Content ● 2. Interpolate with previous step

  38. Neural Turing Machines (NTM) ● 1. Focusing by Content ● 2. Interpolate with previous step ● 3. Convolutional Shift

  39. Neural Turing Machines (NTM) ● 1. Focusing by Content ● 2. Interpolate with previous step ● 3. Convolutional Shift

  40. Neural Turing Machines (NTM) ● 1. Focusing by Content ● 2. Interpolate with previous step ● 3. Convolutional Shift

  41. Neural Turing Machines (NTM) ● 1. Focusing by Content ● 2. Interpolate with previous step ● 3. Convolutional Shift ● 4. Shapening

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Lecture 9: Recurrent Neural Networks Princeton University COS 495 Instructor: Yingyu Liang

Lecture 9: Recurrent Neural Networks Princeton University COS 495 Instructor: Yingyu Liang

Deep Learning Basics Lecture 9: Recurrent Neural Networks Princeton University COS 495 Instructor: Yingyu Liang Introduction Recurrent neural networks Dates back to (Rumelhart et al. , 1986) A family of neural networks for handling

348 views • 34 slides
CHAPTER II I CHAPTER I Recurrent Neural Networks Recurrent Neural Networks CHAPTER II : I :

CHAPTER II I CHAPTER I Recurrent Neural Networks Recurrent Neural Networks CHAPTER II : I :

Ugur HALICI - METU EEE - ANKARA 11/18/2004 CHAPTER II I CHAPTER I Recurrent Neural Networks Recurrent Neural Networks CHAPTER II : I : Recurrent Neural Networks CHAPTER I Recurrent Neural Networks Introduction In this chapter first the

404 views • 27 slides
Computa(on through dynamics Using recurrent neural networks to unveil mechanism in neural

Computa(on through dynamics Using recurrent neural networks to unveil mechanism in neural

Computa(on through dynamics Using recurrent neural networks to unveil mechanism in neural circuits David Sussillo with Valerio Mante and Bill Newsome Table of contents Introduc(on Training recurrent neural networks(RNNs) Understanding how

1.57k views • 105 slides
Lecture 18: Concluding Convolutional Neural Networks, Graphical Models as Foundation for Recurrent

Lecture 18: Concluding Convolutional Neural Networks, Graphical Models as Foundation for Recurrent

Lecture 18: Concluding Convolutional Neural Networks, Graphical Models as Foundation for Recurrent Neural Networks and Bayesian Networks Reference: We will be referring to sections etc of Deep Learning by Yoshua Bengio, Ian J. Goodfellow

974 views • 54 slides
CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks

CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks

CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks Neuron Non-linearity Softmax layer DNN training Loss function and regularization SGD and backprop Learning rate Overfitting

1.8k views • 86 slides
Understanding LSTM Networks Recurrent Neural Networks An unrolled recurrent neural network The

Understanding LSTM Networks Recurrent Neural Networks An unrolled recurrent neural network The

Understanding LSTM Networks Recurrent Neural Networks An unrolled recurrent neural network The Problem of Long-Term Dependencies RNN short-term dependencies Language model trying to predict the next word based on the previous ones the clouds

729 views • 27 slides
Lecture 4: Recurrent neural networks for natural language processing Plan of the lecture Part

Lecture 4: Recurrent neural networks for natural language processing Plan of the lecture Part

Neural Natural Language Processing Lecture 4: Recurrent neural networks for natural language processing Plan of the lecture Part 1 : Language modeling. Part 2 : Recurrent neural networks. Part 3 : Long-Short Term Memory (LSTM).

1.07k views • 78 slides
CS480/680 Lecture 18: July 8, 2019 Recurrent and Recursive Neural Networks [GBC] Chap. 10

CS480/680 Lecture 18: July 8, 2019 Recurrent and Recursive Neural Networks [GBC] Chap. 10

CS480/680 Lecture 18: July 8, 2019 Recurrent and Recursive Neural Networks [GBC] Chap. 10 University of Waterloo CS480/680 Spring 2019 Pascal Poupart 1 Variable length data Traditional feed forward neural networks can only handle fixed

609 views • 18 slides
CSC413/2516 Lecture 7: Generalization & Recurrent Neural Networks Jimmy Ba Jimmy Ba

CSC413/2516 Lecture 7: Generalization & Recurrent Neural Networks Jimmy Ba Jimmy Ba

CSC413/2516 Lecture 7: Generalization & Recurrent Neural Networks Jimmy Ba Jimmy Ba CSC413/2516 Lecture 7: Generalization & Recurrent Neural Networks 1 / 57 Overview Weve focused so far on how to optimize neural nets how to get

971 views • 60 slides
Recurrent Neural Networks Greg Mori - CMPT 419/726 Goodfellow, Bengio, and Courville: Deep

Recurrent Neural Networks Greg Mori - CMPT 419/726 Goodfellow, Bengio, and Courville: Deep

Recurrent Neural Networks Long Short-Term Memory Temporal Convolutional Networks Examples Recurrent Neural Networks Greg Mori - CMPT 419/726 Goodfellow, Bengio, and Courville: Deep Learning textbook Ch. 10 Recurrent Neural Networks Long

667 views • 18 slides
CSC321 Lecture 14: Recurrent Neural Networks Roger Grosse Roger Grosse CSC321 Lecture 14:

CSC321 Lecture 14: Recurrent Neural Networks Roger Grosse Roger Grosse CSC321 Lecture 14:

CSC321 Lecture 14: Recurrent Neural Networks Roger Grosse Roger Grosse CSC321 Lecture 14: Recurrent Neural Networks 1 / 25 Overview Sometimes were interested in predicting sequences Speech-to-text and text-to-speech Caption generation

645 views • 29 slides
CSC321 Lecture 15: Recurrent Neural Networks Roger Grosse Roger Grosse CSC321 Lecture 15:

CSC321 Lecture 15: Recurrent Neural Networks Roger Grosse Roger Grosse CSC321 Lecture 15:

CSC321 Lecture 15: Recurrent Neural Networks Roger Grosse Roger Grosse CSC321 Lecture 15: Recurrent Neural Networks 1 / 26 Overview Sometimes were interested in predicting sequences Speech-to-text and text-to-speech Caption generation

611 views • 28 slides
Recurrent Neural Networks III Milan Straka April 29, 2019 Charles University in Prague Faculty

Recurrent Neural Networks III Milan Straka April 29, 2019 Charles University in Prague Faculty

NPFL114, Lecture 9 Recurrent Neural Networks III Milan Straka April 29, 2019 Charles University in Prague Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics unless otherwise stated Recurrent Neural Networks

864 views • 49 slides
Recurrent Neural Networks CS60010: Deep Learning Abir Das IIT Kharagpur Mar 11, 2020

Recurrent Neural Networks CS60010: Deep Learning Abir Das IIT Kharagpur Mar 11, 2020

Recurrent Neural Networks CS60010: Deep Learning Abir Das IIT Kharagpur Mar 11, 2020 Introduction Recurrent Neural Network LSTM Agenda Get introduced to different recurrent neural architecture e.g. , RNNs, LSTMs, GRUs etc. Get

743 views • 48 slides
CS6501: Deep Learning for Visual Recognition Recurrent Neural Networks (RNNs) Todays Class

CS6501: Deep Learning for Visual Recognition Recurrent Neural Networks (RNNs) Todays Class

CS6501: Deep Learning for Visual Recognition Recurrent Neural Networks (RNNs) Todays Class Recurrent Neural Network Cell Recurrent Neural Networks (RNNs) Bi-Directional Recurrent Neural Networks (Bi-RNNs) Multiple-layer /

583 views • 47 slides
CS6501: Deep Learning for Visual Recognition Recurrent Neural Networks (RNNs) Todays Class

CS6501: Deep Learning for Visual Recognition Recurrent Neural Networks (RNNs) Todays Class

CS6501: Deep Learning for Visual Recognition Recurrent Neural Networks (RNNs) Todays Class Recurrent Neural Network Cell Recurrent Neural Networks (RNNs) Bi-Directional Recurrent Neural Networks (Bi-RNNs) Multiple-layer /

793 views • 21 slides
A Bayesian Approach to Empirical Local Linearization for Robotics Jo-Anne Ting 1 , Aaron

A Bayesian Approach to Empirical Local Linearization for Robotics Jo-Anne Ting 1 , Aaron

A Bayesian Approach to Empirical Local Linearization for Robotics Jo-Anne Ting 1 , Aaron DSouza 2 , Sethu Vijayakumar 3 , Stefan Schaal 1 1 University of Southern California, 2 Google, Inc., 3 University of Edinburgh ICRA 2008 May 23, 2008

583 views • 18 slides
Reinforcement Learning-Based End-to-End Parking for Automatic Parking System CS885

Reinforcement Learning-Based End-to-End Parking for Automatic Parking System CS885

Reinforcement Learning-Based End-to-End Parking for Automatic Parking System CS885 Reinforcement Learning Paper by: P. Zhang, L. Xiong, Z. Yu, P. Fang, S. Yan, J. Yao, and Y. Zhou (Sensors 2019) Presented by: Neel Bhatt Context and

286 views • 14 slides
From Logistic Regression to Neural Networks CMSC 470 Marine Carpuat Logistic Regression What

From Logistic Regression to Neural Networks CMSC 470 Marine Carpuat Logistic Regression What

From Logistic Regression to Neural Networks CMSC 470 Marine Carpuat Logistic Regression What you should know How to make a prediction with logistic regression classifier How to train a logistic regression classifier Machine learning

502 views • 33 slides
Nonlinear Control Strategies for Aircraft Path Following N. Harris McClamroch Department of

Nonlinear Control Strategies for Aircraft Path Following N. Harris McClamroch Department of

Nonlinear Control Strategies for Aircraft Path Following N. Harris McClamroch Department of Aerospace Engineering University of Michigan Ann Arbor, MI 48109 December 12, 2006 S. A. Al-Hiddabi and N. H. McClamroch, Aggressive Longitudinal

370 views • 6 slides
UTIAS C. J. Damaren University of Toronto Institute for Aerospace Studies 4925 Dufferin

UTIAS C. J. Damaren University of Toronto Institute for Aerospace Studies 4925 Dufferin

UTIAS 1/26 An Adaptive Controller for Two Cooperating Flexible Manipulators UTIAS C. J. Damaren University of Toronto Institute for Aerospace Studies 4925 Dufferin Street Toronto, ON M3H 5T6 Canada Presented at the

639 views • 26 slides
Introduction, The PID Controller, State Space Models Automatic Control, Basic Course, Lecture 1

Introduction, The PID Controller, State Space Models Automatic Control, Basic Course, Lecture 1

Introduction, The PID Controller, State Space Models Automatic Control, Basic Course, Lecture 1 Gustav Nilsson 15 November 2016 Lund University, Department of Automatic Control Content 1. Introduction 2. The PID Controller 3. State Space

617 views • 24 slides
Introduction to Pattern Oriented Analysis and Design (POAD) Instructor: Dr. Hany H. Ammar Dept.

Introduction to Pattern Oriented Analysis and Design (POAD) Instructor: Dr. Hany H. Ammar Dept.

Introduction to Pattern Oriented Analysis and Design (POAD) Instructor: Dr. Hany H. Ammar Dept. of Computer Science and Electrical Engineering, WVU Outline Review of Design Patterns The Lifecycle of a Pattern Examples of Design

395 views • 25 slides
The Differentiable Cross-Entropy Method ICML 2020 Br Brandon Amos 1 De Denis is Yarats 12 12 1

The Differentiable Cross-Entropy Method ICML 2020 Br Brandon Amos 1 De Denis is Yarats 12 12 1

The Differentiable Cross-Entropy Method ICML 2020 Br Brandon Amos 1 De Denis is Yarats 12 12 1 Facebook AI Research 2 New York University brandondamos denisyarats bamos.github.io cs.nyu.edu/~dy1042 The cross-entropy method is a powerful

589 views • 20 slides

More recommend