cs6501 deep learning for visual recognition
play

CS6501: Deep Learning for Visual Recognition Recurrent Neural - PowerPoint PPT Presentation

Feb 05, 2024 •565 likes •793 views

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 /

  1. CS6501: Deep Learning for Visual Recognition Recurrent Neural Networks (RNNs)

  2. Today’s Class • Recurrent Neural Network Cell • Recurrent Neural Networks (RNNs) • Bi-Directional Recurrent Neural Networks (Bi-RNNs) • Multiple-layer / Stacked / Deep Bi-Direction Recurrent Neural Networks • LSTMs and GRUs. • Applications in Vision: Caption Generation.

  3. ACM Turing Award 2019 Geoff Hinton Backpropagation Yann LeCun Yoshua Bengio CNNs GANs

  4. Recurrent Neural Network Cell ℎ & ℎ " #$$ ! "

  5. Recurrent Neural Network Cell ℎ " = tanh (. // ℎ & + . /1 ! " ) ℎ & ℎ " #$$ ! "

  6. Recurrent Neural Network Cell 3 " ℎ " ℎ & ℎ " #$$ ℎ " = tanh (. // ℎ & + . /1 ! " ) ! " 3 " = softmax (. /9 ℎ " )

  7. Recurrent Neural Network Cell ' " ℎ " ℎ & ℎ " #$$ ! "

  8. Recurrent Neural Network Cell e (0.7) - $ = [0.1, 0.05, 0.05, 0.1, 0.7] ℎ $ = [0.1 0.2 0 − 0.3 − 0.1 ] ℎ , = [0 0 0 0 0 0 0 ] ℎ $ = [0.1 0.2 0 − 0.3 − 0.1 ] !"" # $ = [0 0 1 0 0] a b c d e c

  9. Recurrent Neural Network Cell ' " ℎ " ℎ & ℎ " #$$ ! "

  10. Recurrent Neural Network Cell ℎ " ℎ & ℎ " #$$ ! "

  11. (Unrolled) Recurrent Neural Network a t <<space>> ) " ) ' ) ( ℎ " ℎ ' ℎ ( ℎ & ℎ " ℎ ' ℎ ( #$$ #$$ #$$ ! " ! ' ! ( c a t

  12. (Unrolled) Recurrent Neural Network cat likes eating ) " ) ' ) ( ℎ " ℎ ' ℎ ( ℎ & ℎ " ℎ ' ℎ ( #$$ #$$ #$$ ! " ! ' ! ( the cat likes

  13. (Unrolled) Recurrent Neural Network positive / negative sentiment rating ) ℎ ( ℎ & ℎ " ℎ ' ℎ ( #$$ #$$ #$$ ! " ! ' ! ( the cat likes

  14. Bidirectional Recurrent Neural Network comer gato quiere + " + ( + * ℎ " ℎ ( ℎ * ℎ ' ℎ " ℎ ( ℎ * #$%% B$%% #$%% ! " ! ( ! * wants the cat

  15. Stacked Recurrent Neural Network ) " ) ' ) ( ℎ " ℎ ' ℎ ( ℎ * ℎ " ℎ ' ℎ ( #$$ #$$ #$$ & " & ' & ( ℎ ℎ ℎ & " & * & ' & ( ℎ ℎ ℎ ℎ #$$ #$$ #$$ ! " ! ' ! ( c a t

  16. Stacked Bidirectional Recurrent Neural Network ) " ) ' ) ( ℎ " ℎ ' ℎ ( ℎ * ℎ " ℎ ' ℎ ( #$$ #$$ #$$ & " & ' & ( ℎ ℎ ℎ & " & * & ' & ( ℎ ℎ ℎ ℎ #$$ #$$ #$$ ! " ! ' ! ( c a t

  17. RNN in Pytorch

  18. LSTM Cell (Long Short-Term Memory) ℎ " ℎ ( #$%& ) ( ) " ! "

  19. LSTM in Pytorch

  20. GRU in Pytorch

  21. Questions? 21

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

CS6501: Deep Learning for Visual Recognition Seq2Seq Model &amp; Text-to-Image Synthesis

CS6501: Deep Learning for Visual Recognition Seq2Seq Model &amp; Text-to-Image Synthesis

CS6501: Deep Learning for Visual Recognition Seq2Seq Model &amp; Text-to-Image Synthesis Presenter: Fuwen Tan Todays Class Mini-batch training of the RNN model Special End-of-Sequence token: &lt;end&gt; Padding

524 views • 40 slides
CS6501: Deep Learning for Visual Recognition Recognizing People in Images Todays Class

CS6501: Deep Learning for Visual Recognition Recognizing People in Images Todays Class

CS6501: Deep Learning for Visual Recognition Recognizing People in Images Todays Class Face Detection Face Matching - and any type of matching Pose estimation Face Detection Face Detection: Viola-Jones Face Detector circa 2001

850 views • 28 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 Object Detection: RCNN, Fast-RCNN, Faster-RCNN

CS6501: Deep Learning for Visual Recognition Object Detection: RCNN, Fast-RCNN, Faster-RCNN

CS6501: Deep Learning for Visual Recognition Object Detection: RCNN, Fast-RCNN, Faster-RCNN Todays Class Object Detection The RCNN Object Detector (2014) The Fast RCNN Object Detector (2015) The Faster RCNN Object Detector

747 views • 29 slides
Visual deep learning models, in particular for face recognition and models of invariant

Visual deep learning models, in particular for face recognition and models of invariant

Visual deep learning models, in particular for face recognition and models of invariant recognition in the ventral stream Center Name Presenter Name Towards a theory of the above tomaso poggio, CBMM, BCS, CSAIL, McGovern MIT Plan

1.14k views • 81 slides
Softmax Classifier + SGD Todays Class Intro to Machine Learning What is Machine Learning?

Softmax Classifier + SGD Todays Class Intro to Machine Learning What is Machine Learning?

CS6501: Deep Learning for Visual Recognition Softmax Classifier + SGD Todays Class Intro to Machine Learning What is Machine Learning? Supervised Learning: Classification with K-nearest neighbors Unsupervised Learning: Clustering with

1.36k views • 91 slides
Deep learning for visual recognition Thurs April 27 Kristen Grauman UT Austin Last time

Deep learning for visual recognition Thurs April 27 Kristen Grauman UT Austin Last time

4/26/2017 Deep learning for visual recognition Thurs April 27 Kristen Grauman UT Austin Last time Support vector machines (wrap-up) Pyramid match kernels Evaluation Scoring an object detector Scoring a multi-class

377 views • 16 slides
Deep Convolutional Networks and their impact on solving large scale visual recognition problems

Deep Convolutional Networks and their impact on solving large scale visual recognition problems

IDA Machine Learning Seminars - Fall 2015 Deep Convolutional Networks and their impact on solving large scale visual recognition problems Hossien Azizpour, Computer Vision Group , KTH . Thanks to: J. Sullivan, A. S. Razavian, A. Maki and S.

1.13k views • 96 slides
Learning Deep Features for Scene Recognition using Places Database Bolei Zhou, Agata Lapedriza,

Learning Deep Features for Scene Recognition using Places Database Bolei Zhou, Agata Lapedriza,

Learning Deep Features for Scene Recognition using Places Database Bolei Zhou, Agata Lapedriza, Jianxiong Xiao, Antonio Torralba, Aude Oliva NIPS2014 Bora elikkale INTRODUCTION Human Visual Recognition Samples world several times / sec

697 views • 20 slides
Visual Learning with Unlabeled Video and Look-Around Policies Kristen Grauman Department of

Visual Learning with Unlabeled Video and Look-Around Policies Kristen Grauman Department of

Visual Learning with Unlabeled Video and Look-Around Policies Kristen Grauman Department of Computer Science University of Texas at Austin Visual recognition: significant recent progress Big labeled Deep learning datasets ImageNet top-5

804 views • 52 slides
Stochastic Gradient Descent (SGD) Todays Class Stochastic Gradient Descent (SGD) SGD Recap

Stochastic Gradient Descent (SGD) Todays Class Stochastic Gradient Descent (SGD) SGD Recap

CS6501: Deep Learning for Visual Recognition Stochastic Gradient Descent (SGD) Todays Class Stochastic Gradient Descent (SGD) SGD Recap Regression vs Classification Generalization / Overfitting / Underfitting Regularization

633 views • 30 slides
Object Recognition/Detection Radovan Fusek 2 nd International summer school on &quot;Deep Learning

Object Recognition/Detection Radovan Fusek 2 nd International summer school on &quot;Deep Learning

Object Recognition/Detection Radovan Fusek 2 nd International summer school on &quot;Deep Learning and Visual Data Analysis&quot; 2018 Our work presented here was partially supported by the EU H2020 686782 PACMAN project, (solved with

1.04k views • 81 slides
DeViSE: A Deep Visual-Semantic Embedding Model Presenters: Ji Gao, Fandi Lin Motivation Visual

DeViSE: A Deep Visual-Semantic Embedding Model Presenters: Ji Gao, Fandi Lin Motivation Visual

DeViSE: A Deep Visual-Semantic Embedding Model Presenters: Ji Gao, Fandi Lin Motivation Visual recognition systems experience problems with large amount of categories. Insufficient labeled training data Blurred distinction between

328 views • 16 slides
Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms

Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms

Deep 3D Representation Learning for Visual Computing Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms Conclusion 2 Outline Overview of 3D deep learning Background 3D deep learning tasks 3D deep

1.66k views • 122 slides
Learning about images from keyword-based Web search CS 395T: Visual Recognition and Search

Learning about images from keyword-based Web search CS 395T: Visual Recognition and Search

Learning about images from keyword-based Web search CS 395T: Visual Recognition and Search February 15, 2008 David Chen Problems with traditional training data for object recognition Time-consuming and difficult to construct Collect

530 views • 32 slides
Knowledge Transfer for Visual Recognition The University of Tokyo RIKEN AIP (Team leader of

Knowledge Transfer for Visual Recognition The University of Tokyo RIKEN AIP (Team leader of

IIT-H and RIKEN-AIP Joint Workshop on Machine Learning and Applications March 15, 2019 Knowledge Transfer for Visual Recognition The University of Tokyo RIKEN AIP (Team leader of Medical Machine Intelligence) Tatsuya Harada Deep Neural Networks

195 views • 15 slides
Bidirectional HTTP Design Implications for HTTP IETF 74 Mark Lentczner, March 2009

Bidirectional HTTP Design Implications for HTTP IETF 74 Mark Lentczner, March 2009

Bidirectional HTTP Design Implications for HTTP IETF 74 Mark Lentczner, March 2009 zero@lindenlab.com Four Approaches XEP-0124: Bidirectional-streams Over Synchronous HTTP, XMPP BOSH http://xmpp.org/extensions/xep-0124.html Bayeux Protocol,

308 views • 12 slides
Framewise Phoneme Classification with Bidirectional LSTM Networks Alex Graves and Jurgen

Framewise Phoneme Classification with Bidirectional LSTM Networks Alex Graves and Jurgen

Framewise Phoneme Classification with Bidirectional LSTM Networks Alex Graves and Jurgen Schmidhuber IJCNN 2005 conference proceedings Chase Duncan Overview 1. Bidirectional LSTM overview 2. What sort of tasks are they appropriate for? 3.

336 views • 15 slides
Low Power Microprocessors Low Power Microprocessors Low Power Technology Gao Wei &amp; Tian

Low Power Microprocessors Low Power Microprocessors Low Power Technology Gao Wei &amp; Tian

Advanced Digital IC Design Outline Why is Low-Power Important? Low Power Microprocessors Low Power Microprocessors Low Power Technology Gao Wei &amp; Tian Youge Conclusions References Low Power Microprocessors, Gao Wei &amp; Tian Youge,

411 views • 6 slides
Board Meeting The Falmouth Historical Society November 17, 2020 Agenda Local History

Board Meeting The Falmouth Historical Society November 17, 2020 Agenda Local History

Board Meeting The Falmouth Historical Society November 17, 2020 Agenda Local History Secretarys Report Communications Treasurers Report Merchandise Committee Reports Programs Museum Buildings &amp; Grounds Museum

310 views • 19 slides
Extending the GC hardware Rob Reilink Extending the GC hardware Why? GC can be an embedded

Extending the GC hardware Rob Reilink Extending the GC hardware Why? GC can be an embedded

Extending the GC hardware Rob Reilink Extending the GC hardware Why? GC can be an embedded computer Home automation Cinema set Car Infotainment system ... But: Essential hardware lacks: Data storage (harddisk and/or flash)

221 views • 9 slides
Cooperation and Contribution of Riga Technical University Faculty of Power and Electrical

Cooperation and Contribution of Riga Technical University Faculty of Power and Electrical

Cooperation and Contribution of Riga Technical University Faculty of Power and Electrical Engineering Institute of Industrial Electronics and Electrical Engineering for COST IC0603 Antenna Systems &amp; Sensors for Information Society

818 views • 61 slides
Deriving Modular Recursion Schemes from Tree Automata Patrick Bahr University of Copenhagen,

Deriving Modular Recursion Schemes from Tree Automata Patrick Bahr University of Copenhagen,

Deriving Modular Recursion Schemes from Tree Automata Patrick Bahr University of Copenhagen, Department of Computer Science paba@diku.dk Computing Science Colloquium, Utrecht University, April 12th, 2012 Outline Tree Automata 1 Bottom-Up

1.37k views • 132 slides
Traitement automatique des langues : Fondements et applications Cours 11 : Neural networks (2)

Traitement automatique des langues : Fondements et applications Cours 11 : Neural networks (2)

Traitement automatique des langues : Fondements et applications Cours 11 : Neural networks (2) Tim Van de Cruys &amp; Philippe Muller 20162017 Introduction Machine learning for NLP Standard approach: linear model trained over

503 views • 37 slides

More recommend