Recursive Sketches for Modular Deep Learning Badih Ghazi, Rina - PowerPoint PPT Presentation

Sep 28, 2022 •24 likes •104 views

Recursive Sketches for Modular Deep Learning Badih Ghazi, Rina Panigrahy, Joshua R. Wang (Google Research) ICML 2019: Long Beach, CA Object Recognition Rich literature around ML techniques for object recognition. Typical problem

Recursive Sketches for Modular Deep Learning Badih Ghazi, Rina Panigrahy, Joshua R. Wang (Google Research) ICML 2019: Long Beach, CA
Object Recognition ● Rich literature around ML techniques for object recognition. ● Typical problem format. Input: Picture ○ ○ Output: Its object(s) Car: 99%
Object Memory ● This talk: twist on typical task. Input: Picture ○ ○ Output: Succinct representation of its object(s) Theorem. Can utilize model that solves the previous ● task as a primitive to solve this task.
Modular Networks 101 Output Module Output Module Cat Atuributes Wall Atuributes ● Module: independent neural network Cat Module Wall Module Wall Module component. ● Modules communicate via one’s output serving as another’s input. Edge Atuributes Edge Atuributes Edge Atuributes ● Intuition. Convolutional Neural Nets first find low-level objects (edge) and Edge Module Edge Module Edge Module build up to high-level objects (cat). The Input Data (Picture) Figure. Abstract view of modular network processing image of a room.
Recursive Sketches ● Our mechanism creates a sketch for each object detected by the modular network. Recursive, because sketch of an ● object incorporates the sketch of sub-objects. ● Sketching tricks: (i) apply random matrix and (ii) take a weighted sum. ● Input represented by top-level sketch .
Provable Sketch Properuies ● Attribute Recovery. Object attributes can be approximately recovered from top-level sketch. ● Sketch-to-Sketch Similarity. Two completely unrelated sketches have small inner product; two sketches with similar objects have large inner product. ● Summary Statistics. If there are multiple objects produced by same module, can approximately recover their summary statistics like count/mean. ● Graceful Erasure. Erasing all but sketch prefix, we still get above properties (but increase recovery error).
Recursable Dictionary Learning ● Previous slide properties required knowing random matrices chosen by the sketch. Recursable Dictionary Learning. Given enough sketches, can approximately ● recover the random matrices (and object attribute vectors). Dictionary learning “unwinds” one level of sketching recursion. ● ● Trickier than Classical Dictionary Learning. The noisy output becomes noisy input for the next stage, so the error guarantee and error tolerance must be of the same form.
Recap: Recursive Sketches ● Takeaway Message. Can utilize model that solves the object recognition as a primitive to generate useful and efficient sketches of inputs. ● Computing our Sketches. Built out of (i) apply random matrix and (ii) take a weighted sum. Let’s chat! Poster #73 @ Pacific ● Ballroom.

Recommend

Modular mul*task reinforcement learning with policy sketches Jacob Andreas, Sergey Levine and Dan

Modular mul*task reinforcement learning with policy sketches Jacob Andreas, Sergey Levine and Dan Klein The learning problem make planks 2 The learning problem make planks make sticks 3 Learning from sketches get wood get wood use saw

1.18k views • 53 slides

RECURSIVE DEEP MODELS FOR SEMANTIC 1 COMPOSITIONALITY Zhicong Lu DGP Lab

RECURSIVE DEEP MODELS FOR SEMANTIC 1 COMPOSITIONALITY Zhicong Lu DGP Lab luzhc@dgp.toronto.edu 1 Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher Manning, Andrew Ng and Christopher Potts. Recursive Deep Models for Semantic

518 views • 29 slides

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

ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP

ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP LEARNING EVERYWHERE INTERNET & CLOUD MEDICINE & BIOLOGY MEDIA & ENTERTAINMENT SECURITY & DEFENSE AUTONOMOUS MACHINES Image

307 views • 26 slides

Recursion 15-110 - Friday 2/21 Learning Objectives Define and recognize base cases and

Recursion 15-110 - Friday 2/21 Learning Objectives Define and recognize base cases and recursive cases in recursive code Read and write basic recursive code Trace over recursive functions that use multiple recursive calls with

940 views • 48 slides

Search Algorithms 15-110 - Monday 2/24 Learning Objectives Trace over recursive functions

Search Algorithms 15-110 - Monday 2/24 Learning Objectives Trace over recursive functions that use multiple recursive calls with Towers of Hanoi Recognize linear search on lists and in recursive contexts Use binary search when reading

465 views • 30 slides

Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice

Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice Scaling up DL 2 What is Deep Learning? 3 DEEP LEARNING EVERYWHERE INTERNET & CLOUD MEDICINE & BIOLOGY SECURITY & DEFENSE MEDIA &

1.45k views • 39 slides

Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning

Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning Methods) Peter Henderson Statistical Society of Canada Annual Meeting 2018 Contributors Riashat Islam Phil Bachman Doina Precup David Meger Joelle

850 views • 37 slides

Natural Language Processing with Deep Learning CS224N/Ling284 Christopher Manning Lecture 18:

Natural Language Processing with Deep Learning CS224N/Ling284 Christopher Manning Lecture 18: Tree Recursive Neural Networks, Constituency Parsing, and Sentiment Lecture Plan: Lecture 18: Tree Recursive Neural Networks, Constituency Parsing,

889 views • 75 slides

Natural Language Processing with Deep Learning CS224N/Ling284 Christopher Manning Lecture 18:

878 views • 73 slides

Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI

Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI Mission Helping people solve challenging problems using AI and deep learning. Developers, data scientists and engineers Self-driving cars,

1.44k views • 72 slides

Physical Sketches CPSC 581 - Fall 2015 Motivation Experience your sketches in a more physical

Physical Sketches CPSC 581 - Fall 2015 Motivation Experience your sketches in a more physical form Test your interaction design with potential end-users Better insights by exploring in 3D! Architecture scale model Industrial Design

417 views • 27 slides

Deep Neural Networks and Deep Reinforcement Learning Deep Learning, Goodfellow, Bengio and

Deep Neural Networks and Deep Reinforcement Learning Deep Neural Networks and Deep Reinforcement Learning Deep Learning, Goodfellow, Bengio and Courville [chapt. 6,7,8]; AIMA [sect. 21.1-21.3]; Sutton and Barto, Reinforcement Learning: an

527 views • 35 slides

Natural Language Processing with Deep Learning CS224N The Future of Deep Learning + NLP Kevin

Natural Language Processing with Deep Learning CS224N The Future of Deep Learning + NLP Kevin Clark Deep Learning for NLP 5 years ago No Seq2Seq No Attention No large-scale QA/reading comprehension datasets No TensorFlow or

1.41k views • 92 slides

An Overview of Deep Residual Learning Semih Yagcioglu 01.03.2016 Deep Residual Learning

An Overview of Deep Residual Learning Semih Yagcioglu 01.03.2016 Deep Residual Learning Microsoft Research Asia (MSRA) Kaiming He, Xiangyu Zhang, Shaoqing Ren, & Jian Sun. Deep Residual Learning for Image Recognition. arXiv

1.32k views • 54 slides

Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree

Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree Search, Nature 2016] CS 486/686 University of Waterloo Lecture 21: July 12, 2017 Outline AlphaGo Supervised Learning of Policy Networks

540 views • 15 slides

Mocha.jl Deep Learning in Julia Chiyuan Zhang (@pluskid) CSAIL, MIT Deep Learning Learning

Mocha.jl Deep Learning in Julia Chiyuan Zhang (@pluskid) CSAIL, MIT Deep Learning Learning with multi-layer (3~30) neural networks, on a huge training set. State-of-the-art on many AI tasks Computer Vision : Image Classification,

1.53k views • 23 slides

Minjie Wang Deep Learning Deep Learning trend in the past 10 years Caffe State-of-art DL

Tofu: Parallelizing Deep Learning Systems with Automatic Tiling Minjie Wang Deep Learning Deep Learning trend in the past 10 years Caffe State-of-art DL system is based on dataflow GPU#0 w1 w2 data g1 g2 Forward propagation

405 views • 38 slides

Deep Learning: Theory and Practice Deep Learning - Practical 02-04-2020 Considerations

Deep Learning: Theory and Practice Deep Learning - Practical 02-04-2020 Considerations deeplearning.cce2020@gmail.com Deep Networks Intuition Neural networks with multiple hidden layers - Deep networks [Hinton, 2006] Deep Networks Intuition

1.33k views • 28 slides

Deep Learning: State of the Art (2020) Deep Learning Lecture Series https://deeplearning.mit.edu

Deep Learning: State of the Art (2020) Deep Learning Lecture Series https://deeplearning.mit.edu 2020 For the full list of references visit: http://bit.ly/deeplearn-sota-2020 Outline Deep Learning Growth, Celebrations, and Limitations

1.1k views • 87 slides

12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from

12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from Wanli Ouyang, Zsolt Kira, Lawrence Neal, Raymond Yeh, Junting Lou and Teck-Yian Lim Unsupervised Learning in General Unsupervised learning is

1.48k views • 115 slides

Regularization for Deep Learning Lecture slides for Chapter 7 of Deep Learning

Regularization for Deep Learning Lecture slides for Chapter 7 of Deep Learning www.deeplearningbook.org Ian Goodfellow 2016-09-27 Definition Regularization is any modification we make to a learning algorithm that is intended to reduce

179 views • 13 slides

Introduction to Deep Learning Outline Deep Learning RNN CNN Attention

Introduction to Deep Learning Outline Deep Learning RNN CNN Attention Transformer Pytorch Introduction Basics Examples RNNs Some slides borrowed from Fei-Fei Li & Justin Johnson &

1.1k views • 55 slides

Recursive Methods Noter ch.2 Recursive Methods Recursive problem solution Problems

Recursive Methods Noter ch.2 Recursive Methods Recursive problem solution Problems that are naturally solved by recursion Examples: Recursive function: Fibonacci numbers Recursive graphics: Fractals Mutual recursion:

796 views • 61 slides