library learning for neurally guided bayesian program
play

Library Learning for Neurally-Guided Bayesian Program Induction Kevin - PowerPoint PPT Presentation

Oct 29, 2022 •358 likes •579 views

Library Learning for Neurally-Guided Bayesian Program Induction Kevin Ellis 1 , Lucas Morales 1 , Mathias Sabl e-Meyer 2 , Armando Solar-Lezama 1 , Joshua B. Tenenbaum 1 1 : MIT. 2 : ENS Paris-Saclay. Symbolic regression: List processing: Text

  1. Library Learning for Neurally-Guided Bayesian Program Induction Kevin Ellis 1 , Lucas Morales 1 , Mathias Sabl´ e-Meyer 2 , Armando Solar-Lezama 1 , Joshua B. Tenenbaum 1 1 : MIT. 2 : ENS Paris-Saclay. Symbolic regression: List processing: Text editing: [5 2 9] → [9 2 5] P Kohli → Dr. Kohli Sumit Gulwani → Dr. Gulwani [1 1 2 2] → [2 2 1 1] ax 3 + bx 2 + [1 2 3 2] → [2 3 2 1] Danny Tarlow → Dr. Tarlow a / ( x − b ) cx + d Explore/Compress/Compile (EC 2 ) learns to solve programming tasks like these by growing a library of code and training a neural net to search for programs written using the library

  2. Library learning [7 2 3] → [7 3] [1 2 3 4] → [3 4] [4 3 2 1] → [4 3]

  3. Library learning [7 2 3] → [7 3] [1 2 3 4] → [3 4] [4 3 2 1] → [4 3] Library: f 1 ( ℓ, p ) = (foldr ℓ nil ( λ (x a) (if (p x) (cons x a) a))) ( f 1 : Higher-order filter function ) ( Get elements x from ℓ where (p x ) returns true )

  4. Library learning [7 2 3] → [7 3] [1 2 3 4] → [3 4] [4 3 2 1] → [4 3] f ( ℓ ) = ( f 1 ℓ ( λ (x) (> x 2))) Library: f 1 ( ℓ, p ) = (foldr ℓ nil ( λ (x a) (if (p x) (cons x a) a))) ( f 1 : Higher-order filter function ) ( Get elements x from ℓ where (p x ) returns true )

  5. Subset of 38 learned library routines for list processing f 0 ( ℓ, r ) = (foldr r ℓ cons) f 0 : Append lists r and ℓ f 1 ( ℓ, p ) = (foldr ℓ nil ( λ (x a) f 1 : Higher-order filter function (if (p x) (cons x a) a))) f 2 ( ℓ ) = (foldr ℓ 0 ( λ (x a) f 2 : Maximum element in list ℓ (if (> a x) a x))) f 3 ( ℓ, k ) = (foldr ℓ (is-nil ℓ ) f 2 : Whether ℓ contains k ( λ (x a) (if a a (= k x))))

  6. Explore/Compress/Compile as Bayesian Inference DSL prog prog prog task task task

  7. Explore/Compress/Compile as Amortized Bayesian Inference DSL is prog prog prog task task task

  8. Explore /Compress/Compile as Amortized Bayesian Inference Explore : Infer programs, fixing DSL and neural recognition model DSL is prog prog prog task task task

  9. Explore /Compress/Compile as Amortized Bayesian Inference Explore : Infer programs, fixing DSL and neural recognition model DSL f 1 , f 2 , ... Programs: Neurally-Guided Enumerative Search ( f 1 ℓ ( λ (x) (> x 2))) Recog. Task model [7 2 3] → [7 3] [1 2 3 4] → [3 4] [4 3 2 1] → [4 3] is DSL prog prog prog task task task

  10. Explore/ Compress /Compile as Amortized Bayesian Inference Compress : Update DSL, fixing programs DSL is prog prog prog task task task

  11. Explore/ Compress /Compile as Amortized Bayesian Inference Compress : Update DSL, fixing programs progs. for task 1 DSL+ progs. for task 2 cons 1 + 1 DSL + 1 + car z 1 DSL is prog prog prog task task task

  12. Explore/Compress/ Compile as Amortized Bayesian Inference Compile : Train recognition model DSL is prog prog prog task task task

  13. Explore/Compress/ Compile as Amortized Bayesian Inference Compile : Train recognition model sample run program DSL task DSL is prog prog prog task task task

  14. Explore/Compress/Compile as Amortized Bayesian Inference Explore DSL is prog prog prog task task task DSL DSL prog prog prog prog prog prog task task task task task task Compress Compile

  15. Domain: Text Editing In the style of FlashFill (Gulwani 2012). Starts with map , fold , etc. Input Output +106 769-438 106.769.438 +83 973-831 83.973.831 Temple Anna H TAH Lara Gregori LG

  16. Text editing: Library learning builds on itself Learned DSL primitives over 3 iterations (3 columns). Learned primitives call each other (arrows).

  17. Programs with numerical parameters: Symbolic regression from visual input Fits parameters by autograd-ing thru program Recognition model looks at picture of function’s graph Programs & Tasks DSL f 0 ( x ) = (+ x real) f 1 ( x ) = ( f 0 (* real x)) f 2 ( x ) = ( f 1 (* x ( f 0 x))) f ( x ) = ( f 1 x) f ( x ) = ( f 5 x) f 3 ( x ) = ( f 0 (* x ( f 2 x))) f 4 ( x ) = ( f 0 (* x ( f 3 x))) (f 4 : 4th order polynomial) f 5 ( x ) = (/ real ( f 0 x)) f ( x ) = ( f 4 x) f ( x ) = ( f 3 x) (f 5 : rational function)

  18. New domain: Generative graphics programs (Turtle/LOGO) Training tasks:

  19. Generative graphics programs: Samples from DSL DSL samples before learning DSL samples after learning

  20. Generative graphics programs: Learned library contains parametric drawing routines Semicircle: Spiral: Greek Spiral: S-Curves: Polygons & Stars: Circles:

  21. Learning to program: Poster AB #24

Recommend

Bayesian Learning for Guided Direct Illumination Sampling Vvoda , Kondapaneni, Kivnek -

Bayesian Learning for Guided Direct Illumination Sampling Vvoda , Kondapaneni, Kivnek -

1 Bayesian Learning for Guided Direct Illumination Sampling Vvoda , Kondapaneni, Kivnek - Bayesian online regression for adaptive illumination sampling 2 Guiding needs radiance approximations How to learn them reliably ? Our

594 views • 58 slides
Neurally-Guided Structure Inference http://ngsi.csail.mit.edu Sidi Lu*, Jiayuan Mao*, Josh

Neurally-Guided Structure Inference http://ngsi.csail.mit.edu Sidi Lu*, Jiayuan Mao*, Josh

Neurally-Guided Structure Inference http://ngsi.csail.mit.edu Sidi Lu*, Jiayuan Mao*, Josh Tenenbaum, and Jiajun Wu (* indicates equal contributions) Structure Inference Structure Inference Data [Kemp et al. 2008] Structure Inference Data

925 views • 38 slides
Bayesian Learning 1 Outline MLE, MAP vs. Bayesian Learning Bayesian Linear Regression

Bayesian Learning 1 Outline MLE, MAP vs. Bayesian Learning Bayesian Linear Regression

Bayesian Learning 1 Outline MLE, MAP vs. Bayesian Learning Bayesian Linear Regression Bayesian Gaussian Mixture Models Non-parametric Bayes 2 Take Away ... 1. Maximum Likelihood Estimate (MLE) = arg max p ( D| )

609 views • 27 slides
for Active Learning Guided Inquiry Learning The POGIL Project Process Oriented, Guided

for Active Learning Guided Inquiry Learning The POGIL Project Process Oriented, Guided

Innovative Teaching Methods for Active Learning Guided Inquiry Learning The POGIL Project Process Oriented, Guided Inquiry Learning Developed in college Chemistry classrooms (1994), has since expanded to other fields and into high

489 views • 10 slides
Its like stickers in your brain: Using the Guided Inquiry Process to Support Lifelong

Its like stickers in your brain: Using the Guided Inquiry Process to Support Lifelong

Its like stickers in your brain: Using the Guided Inquiry Process to Support Lifelong Learning Skills in an Australian School Library Kasey Garrison & Lee FitzGerald What is Guided Inquiry (GI)? Pedagogy grounded in a

543 views • 21 slides
Outline Intro to RL and Bayesian Learning History of Bayesian RL Model-based Bayesian

Outline Intro to RL and Bayesian Learning History of Bayesian RL Model-based Bayesian

Outline Intro to RL and Bayesian Learning History of Bayesian RL Model-based Bayesian RL Prior knowledge, policy optimization, discussion, Bayesian approaches for other RL variants Model-free Bayesian RL Gaussian

1.23k views • 63 slides
CS440/ECE448 Lecture 15: Bayesian Inference and Bayesian Learning Slides by Svetlana Lazebnik,

CS440/ECE448 Lecture 15: Bayesian Inference and Bayesian Learning Slides by Svetlana Lazebnik,

CS440/ECE448 Lecture 15: Bayesian Inference and Bayesian Learning Slides by Svetlana Lazebnik, 10/2016 Modified by Mark Hasegawa-Johnson, 3/2019 Bayesian Inference and Bayesian Learning Bayes Rule Bayesian Inference Misdiagnosis

829 views • 38 slides
Learning Objectives At the end of the class you should be able to: derive Bayesian learning from

Learning Objectives At the end of the class you should be able to: derive Bayesian learning from

Learning Objectives At the end of the class you should be able to: derive Bayesian learning from first principles explain how the Beta and Dirichlet distributions are used for Bayesian learning. D. Poole and A. Mackworth 2019 c Artificial

272 views • 16 slides
Adversarial Approaches to Bayesian Learning and Bayesian Approaches to Adversarial Robustness

Adversarial Approaches to Bayesian Learning and Bayesian Approaches to Adversarial Robustness

Adversarial Approaches to Bayesian Learning and Bayesian Approaches to Adversarial Robustness Ian Goodfellow, OpenAI Research Scientist NIPS 2016 Workshop on Bayesian Deep Learning Barcelona, 2016-12-10 Speculation on Three Topics Can we

769 views • 21 slides
Beyond Uniform Priors in Bayesian Network Structure Learning (for Discrete Bayesian Networks)

Beyond Uniform Priors in Bayesian Network Structure Learning (for Discrete Bayesian Networks)

Beyond Uniform Priors in Bayesian Network Structure Learning (for Discrete Bayesian Networks) Marco Scutari scutari@stats.ox.ac.uk Department of Statistics University of Oxford April 5, 2017 Bayesian Network Structure Learning Learning a BN

536 views • 26 slides
Bayesian learning (with a recap of Bayesian Networks) Applied artificial intelligence (EDA132)

Bayesian learning (with a recap of Bayesian Networks) Applied artificial intelligence (EDA132)

Bayesian learning (with a recap of Bayesian Networks) Applied artificial intelligence (EDA132) Lecture 05 2016-02-02 Elin A. Topp Material based on course book, chapters 14.1-3, 20, and on Tom M. Mitchell, Machine Learning, McGraw-Hill,

557 views • 28 slides
Overview Bayesian Methods for Parameter Estimation Introduction to Bayesian Statistics: Learning

Overview Bayesian Methods for Parameter Estimation Introduction to Bayesian Statistics: Learning

Overview Bayesian Methods for Parameter Estimation Introduction to Bayesian Statistics: Learning a Probability Learning the mean of a Gaussian Chris Williams Readings: Bishop 2.1 (Beta), 2.2 (Dirichlet), 2.3.6 School of Informatics,

177 views • 5 slides
Should all Machine Learning be Bayesian? Should all Bayesian models be non-parametric? Zoubin

Should all Machine Learning be Bayesian? Should all Bayesian models be non-parametric? Zoubin

Should all Machine Learning be Bayesian? Should all Bayesian models be non-parametric? Zoubin Ghahramani Department of Engineering University of Cambridge, UK zoubin@eng.cam.ac.uk http://learning.eng.cam.ac.uk/zoubin/ BARK 2008 Some

456 views • 26 slides
The Embedded Learning Library The Embedded Learning Library (ELL) Cross-compiler for AI

The Embedded Learning Library The Embedded Learning Library (ELL) Cross-compiler for AI

The Embedded Learning Library The Embedded Learning Library (ELL) Cross-compiler for AI pipelines, specialized for resource constrained target platforms T arget ELL AI Machine Pipeline Code https://github.com/Microsoft/ELL The Embedded

638 views • 36 slides
Learning: A Bayesian solution Dmitry P. Vetrov Research professor at HSE, Head of Bayesian

Learning: A Bayesian solution Dmitry P. Vetrov Research professor at HSE, Head of Bayesian

Open Problems in Deep Learning: A Bayesian solution Dmitry P. Vetrov Research professor at HSE, Head of Bayesian methods research group http://bayesgroup.ru Idea of the talk 2 Deep Learning Revolution in machine learning Deep neural

452 views • 26 slides
CSCE 478/878 Lecture 6: Bayesian Learning MAP learners 1. Provide practical learning

CSCE 478/878 Lecture 6: Bayesian Learning MAP learners 1. Provide practical learning

Bayesian Methods Not all hypotheses are created equal (even if they are all Outline consistent with the training data) Might have reasons (domain information) to favor some Bayes Theorem hypotheses over others a priori Bayesian methods work

201 views • 6 slides
Probabilistic Graphical Models Lecture 5 Bayesian Learning of Bayesian Networks CS/CNS/EE

Probabilistic Graphical Models Lecture 5 Bayesian Learning of Bayesian Networks CS/CNS/EE

Probabilistic Graphical Models Lecture 5 Bayesian Learning of Bayesian Networks CS/CNS/EE 155 Andreas Krause Announcements Recitations: Every Tuesday 4-5:30 in 243 Annenberg Homework 1 out. Due in class Wed Oct 21 Project proposals due

521 views • 41 slides
2016-02-10 5.2 Learning Bayesian networks: Learning phase: General idea Representing and

2016-02-10 5.2 Learning Bayesian networks: Learning phase: General idea Representing and

2016-02-10 5.2 Learning Bayesian networks: Learning phase: General idea Representing and storing the knowledge See Witten et al. 2011. The network we want to learn has to have a node for every feature that we have, resp. want to be Bayesian

58 views • 4 slides
Function Space Priors in Bayesian Deep Learning Roger Grosse Motivation Today Bayesian deep

Function Space Priors in Bayesian Deep Learning Roger Grosse Motivation Today Bayesian deep

Function Space Priors in Bayesian Deep Learning Roger Grosse Motivation Today Bayesian deep learning is most often tested on regularization (Bayesian Occams Razor, description length regularization) smoothing the predictions

420 views • 25 slides
AND MACHINE LEARNING CHAPTER 8: GRAPHICAL MODELS Bayesian Networks Directed Acyclic Graph (DAG)

AND MACHINE LEARNING CHAPTER 8: GRAPHICAL MODELS Bayesian Networks Directed Acyclic Graph (DAG)

PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 8: GRAPHICAL MODELS Bayesian Networks Directed Acyclic Graph (DAG) Bayesian Networks General Factorization Bayesian Curve Fitting (1) Polynomial Bayesian Curve Fitting (2) Plate Bayesian

846 views • 71 slides
Guided by Values: Creating an Open Values Statement Tina Baich IUPUI University Library CNI

Guided by Values: Creating an Open Values Statement Tina Baich IUPUI University Library CNI

Guided by Values: Creating an Open Values Statement Tina Baich IUPUI University Library CNI Virtual Spring Member Meeting April 14, 2020 How did this start? Inspiration University of California Libraries STAR Team Choosing Pathways to Open

391 views • 26 slides
Reach and grasp by people with tetraplegia using a neurally controlled robotic arm Nature, 17

Reach and grasp by people with tetraplegia using a neurally controlled robotic arm Nature, 17

Leigh R. Hochberg et al. Reach and grasp by people with tetraplegia using a neurally controlled robotic arm Nature, 17 May 2012 Paper overview Ilya Kuzovkin 11 April 2014, Tartu etc How it works? etc Reach and grasp by people with

1.08k views • 51 slides
Foundations of AI Why learning works 1 6 . Statistical Machine Learning Bayesian Learning and

Foundations of AI Why learning works 1 6 . Statistical Machine Learning Bayesian Learning and

Contents Statistical learning Foundations of AI Why learning works 1 6 . Statistical Machine Learning Bayesian Learning and Why Learning Works W olfram Burgard, Bernhard Nebel, and Andreas Karw ath 10/ 1 10/ 2 Statistical Learning

305 views • 5 slides
Pacemaker therapy for patients with neurally-mediated syncope and documented asystole A

Pacemaker therapy for patients with neurally-mediated syncope and documented asystole A

ISSUE 3 SYNCOPE ISSUE 3 I nternational S tudy on S yncope of U ncertain E tiology 3 Pacemaker therapy for patients with neurally-mediated syncope and documented asystole A randomized controlled double-blind trial ISSUE 3 Study design

139 views • 9 slides

More recommend