automatic learning with feedback queries
play

Automatic Learning with Feedback Queries Automatic Refers to - PowerPoint PPT Presentation

May 20, 2023 •47 likes •577 views

Automatic Learning with Feedback Queries Automatic Refers to Accepted by Finite Automata John Case 1 Sanjay Jain 2 Yuh Shin Ong 2 Pavel Semukhin 3 Frank Stephan 2 1 University of Delaware 2 National University of Singapore 3 University of Regina

  1. Automatic Learning with Feedback Queries Automatic Refers to Accepted by Finite Automata John Case 1 Sanjay Jain 2 Yuh Shin Ong 2 Pavel Semukhin 3 Frank Stephan 2 1 University of Delaware 2 National University of Singapore 3 University of Regina Computability in Europe 2011 Sofia, Bulgaria

  2. For Your Speed Reading Pleasure & Quick Impression ( .. ⌣ ) 1 Background Motivation & Numerical Example Semi Computability-Theoretic Setting Learnable Classes of Regular Languages 2 Automatic Structures & Learning Automatic Structures Automatic Classes Learning Automatic Classes & Further Motivation Memory Restrictions Formulate Automatic Feedback Learning 3 Examples & Results Examples Results CJOSS (UD, NUS, UR) Auto Learn w/ Feedback Queries CiE’11, Sofia, Bulgaria 2 / 13

  3. Background Motivation & Example Motivation & Numerical Example A motivation: Program of Khoussainov & Nerode 1995 re ≈ effect of replacing TMs by finite automata in computable model theory. Present paper: One in a series (Jain, Luo and Stephan 2010; Jain, Ong, Pu, Stephan 2010; Case, Jain, Le, Ong, Semukhin, Stephan LATA-2011) devoted to effect on computability-theoretic learning theory under above replacement. Example unrestricted learning from positive data: Data Hypotheses 2 Set of all even numbers; 2,3 Set of all numbers; 2,3,5 Set of all prime numbers; 2,3,5,13 Set of all prime numbers; 2,3,5,13,1 Set of all Fibonacci numbers; 2,3,5,13,1,8 Set of all Fibonacci numbers. . . . . . . Success: Algorithmic learner outputs a sequence of hypotheses which eventually stabilizes on a correct hypothesis. CJOSS (UD, NUS, UR) Auto Learn w/ Feedback Queries CiE’11, Sofia, Bulgaria 3 / 13

  4. Background Motivation & Example Motivation & Numerical Example A motivation: Program of Khoussainov & Nerode 1995 re ≈ effect of replacing TMs by finite automata in computable model theory. Present paper: One in a series (Jain, Luo and Stephan 2010; Jain, Ong, Pu, Stephan 2010; Case, Jain, Le, Ong, Semukhin, Stephan LATA-2011) devoted to effect on computability-theoretic learning theory under above replacement. Example unrestricted learning from positive data: Data Hypotheses 2 Set of all even numbers; 2,3 Set of all numbers; 2,3,5 Set of all prime numbers; 2,3,5,13 Set of all prime numbers; 2,3,5,13,1 Set of all Fibonacci numbers; 2,3,5,13,1,8 Set of all Fibonacci numbers. . . . . . . Success: Algorithmic learner outputs a sequence of hypotheses which eventually stabilizes on a correct hypothesis. CJOSS (UD, NUS, UR) Auto Learn w/ Feedback Queries CiE’11, Sofia, Bulgaria 3 / 13

  5. Background Motivation & Example Motivation & Numerical Example A motivation: Program of Khoussainov & Nerode 1995 re ≈ effect of replacing TMs by finite automata in computable model theory. Present paper: One in a series (Jain, Luo and Stephan 2010; Jain, Ong, Pu, Stephan 2010; Case, Jain, Le, Ong, Semukhin, Stephan LATA-2011) devoted to effect on computability-theoretic learning theory under above replacement. Example unrestricted learning from positive data: Data Hypotheses 2 Set of all even numbers; 2,3 Set of all numbers; 2,3,5 Set of all prime numbers; 2,3,5,13 Set of all prime numbers; 2,3,5,13,1 Set of all Fibonacci numbers; 2,3,5,13,1,8 Set of all Fibonacci numbers. . . . . . . Success: Algorithmic learner outputs a sequence of hypotheses which eventually stabilizes on a correct hypothesis. CJOSS (UD, NUS, UR) Auto Learn w/ Feedback Queries CiE’11, Sofia, Bulgaria 3 / 13

  6. Background Motivation & Example Motivation & Numerical Example A motivation: Program of Khoussainov & Nerode 1995 re ≈ effect of replacing TMs by finite automata in computable model theory. Present paper: One in a series (Jain, Luo and Stephan 2010; Jain, Ong, Pu, Stephan 2010; Case, Jain, Le, Ong, Semukhin, Stephan LATA-2011) devoted to effect on computability-theoretic learning theory under above replacement. Example unrestricted learning from positive data: Data Hypotheses 2 Set of all even numbers; 2,3 Set of all numbers; 2,3,5 Set of all prime numbers; 2,3,5,13 Set of all prime numbers; 2,3,5,13,1 Set of all Fibonacci numbers; 2,3,5,13,1,8 Set of all Fibonacci numbers. . . . . . . Success: Algorithmic learner outputs a sequence of hypotheses which eventually stabilizes on a correct hypothesis. CJOSS (UD, NUS, UR) Auto Learn w/ Feedback Queries CiE’11, Sofia, Bulgaria 3 / 13

  7. Background Motivation & Example Motivation & Numerical Example A motivation: Program of Khoussainov & Nerode 1995 re ≈ effect of replacing TMs by finite automata in computable model theory. Present paper: One in a series (Jain, Luo and Stephan 2010; Jain, Ong, Pu, Stephan 2010; Case, Jain, Le, Ong, Semukhin, Stephan LATA-2011) devoted to effect on computability-theoretic learning theory under above replacement. Example unrestricted learning from positive data: Data Hypotheses 2 Set of all even numbers; 2,3 Set of all numbers; 2,3,5 Set of all prime numbers; 2,3,5,13 Set of all prime numbers; 2,3,5,13,1 Set of all Fibonacci numbers; 2,3,5,13,1,8 Set of all Fibonacci numbers. . . . . . . Success: Algorithmic learner outputs a sequence of hypotheses which eventually stabilizes on a correct hypothesis. CJOSS (UD, NUS, UR) Auto Learn w/ Feedback Queries CiE’11, Sofia, Bulgaria 3 / 13

  8. Background Motivation & Example Motivation & Numerical Example A motivation: Program of Khoussainov & Nerode 1995 re ≈ effect of replacing TMs by finite automata in computable model theory. Present paper: One in a series (Jain, Luo and Stephan 2010; Jain, Ong, Pu, Stephan 2010; Case, Jain, Le, Ong, Semukhin, Stephan LATA-2011) devoted to effect on computability-theoretic learning theory under above replacement. Example unrestricted learning from positive data: Data Hypotheses 2 Set of all even numbers; 2,3 Set of all numbers; 2,3,5 Set of all prime numbers; 2,3,5,13 Set of all prime numbers; 2,3,5,13,1 Set of all Fibonacci numbers; 2,3,5,13,1,8 Set of all Fibonacci numbers. . . . . . . Success: Algorithmic learner outputs a sequence of hypotheses which eventually stabilizes on a correct hypothesis. CJOSS (UD, NUS, UR) Auto Learn w/ Feedback Queries CiE’11, Sofia, Bulgaria 3 / 13

  9. Background Motivation & Example Motivation & Numerical Example A motivation: Program of Khoussainov & Nerode 1995 re ≈ effect of replacing TMs by finite automata in computable model theory. Present paper: One in a series (Jain, Luo and Stephan 2010; Jain, Ong, Pu, Stephan 2010; Case, Jain, Le, Ong, Semukhin, Stephan LATA-2011) devoted to effect on computability-theoretic learning theory under above replacement. Example unrestricted learning from positive data: Data Hypotheses 2 Set of all even numbers; 2,3 Set of all numbers; 2,3,5 Set of all prime numbers; 2,3,5,13 Set of all prime numbers; 2,3,5,13,1 Set of all Fibonacci numbers; 2,3,5,13,1,8 Set of all Fibonacci numbers. . . . . . . Success: Algorithmic learner outputs a sequence of hypotheses which eventually stabilizes on a correct hypothesis. CJOSS (UD, NUS, UR) Auto Learn w/ Feedback Queries CiE’11, Sofia, Bulgaria 3 / 13

  10. Background Motivation & Example Motivation & Numerical Example A motivation: Program of Khoussainov & Nerode 1995 re ≈ effect of replacing TMs by finite automata in computable model theory. Present paper: One in a series (Jain, Luo and Stephan 2010; Jain, Ong, Pu, Stephan 2010; Case, Jain, Le, Ong, Semukhin, Stephan LATA-2011) devoted to effect on computability-theoretic learning theory under above replacement. Example unrestricted learning from positive data: Data Hypotheses 2 Set of all even numbers; 2,3 Set of all numbers; 2,3,5 Set of all prime numbers; 2,3,5,13 Set of all prime numbers; 2,3,5,13,1 Set of all Fibonacci numbers; 2,3,5,13,1,8 Set of all Fibonacci numbers. . . . . . . Success: Algorithmic learner outputs a sequence of hypotheses which eventually stabilizes on a correct hypothesis. CJOSS (UD, NUS, UR) Auto Learn w/ Feedback Queries CiE’11, Sofia, Bulgaria 3 / 13

  11. Background Motivation & Example Motivation & Numerical Example A motivation: Program of Khoussainov & Nerode 1995 re ≈ effect of replacing TMs by finite automata in computable model theory. Present paper: One in a series (Jain, Luo and Stephan 2010; Jain, Ong, Pu, Stephan 2010; Case, Jain, Le, Ong, Semukhin, Stephan LATA-2011) devoted to effect on computability-theoretic learning theory under above replacement. Example unrestricted learning from positive data: Data Hypotheses 2 Set of all even numbers; 2,3 Set of all numbers; 2,3,5 Set of all prime numbers; 2,3,5,13 Set of all prime numbers; 2,3,5,13,1 Set of all Fibonacci numbers; 2,3,5,13,1,8 Set of all Fibonacci numbers. . . . . . . Success: Algorithmic learner outputs a sequence of hypotheses which eventually stabilizes on a correct hypothesis. CJOSS (UD, NUS, UR) Auto Learn w/ Feedback Queries CiE’11, Sofia, Bulgaria 3 / 13

Recommend

Queries in PSM The following rules apply to the use of queries: CS 235: 1. Queries

Queries in PSM The following rules apply to the use of queries: CS 235: 1. Queries

Queries in PSM The following rules apply to the use of queries: CS 235: 1. Queries returning a single value can be Introduction to Databases used in assignments 2. Queries returning a single tuple can be used Svetlozar Nestorov with

530 views • 4 slides
4303 Ed/Serious Feedback and Reinforcement Feedback and Reinforcement Both of them are

4303 Ed/Serious Feedback and Reinforcement Feedback and Reinforcement Both of them are

4303 Ed/Serious Feedback and Reinforcement Feedback and Reinforcement Both of them are the most important concepts in learning. Any differences? Feedback Feedback involves providing learners with information about their

710 views • 24 slides
Real-Time Feedback Optimization of Power Systems Florian Drfler Automatic Control Laboratory,

Real-Time Feedback Optimization of Power Systems Florian Drfler Automatic Control Laboratory,

Real-Time Feedback Optimization of Power Systems Florian Drfler Automatic Control Laboratory, ETH Zrich 1 Acknowledgements Adrian Hauswirth Saverio Bolognani Gabriela Hug 2 feedforward optimization vs. feedback control d estimate d

1.06k views • 54 slides
Automatic diagnosis and feedback for lexical stress errors in non-native speech: Towards a CAPT

Automatic diagnosis and feedback for lexical stress errors in non-native speech: Towards a CAPT

Automatic diagnosis and feedback for lexical stress errors in non-native speech: Towards a CAPT system for French learners of German Anjana Sofia Vakil Department of Computational Linguistics and Phonetics University of Saarland, Saarbr

539 views • 51 slides
A Hands-On Introduction to Automatic Machine Learning Lars Kotthofg University of Wyoming

A Hands-On Introduction to Automatic Machine Learning Lars Kotthofg University of Wyoming

A Hands-On Introduction to Automatic Machine Learning Lars Kotthofg University of Wyoming larsko@uwyo.edu AutoML Workshop, 28 August 2018, Nanjing 1 Machine Learning Data Machine Learning Predictions 2 Automatic Machine Learning

744 views • 33 slides
Structure' Learning' Daphne Koller Why Structure Learning To learn model for new queries,

Structure' Learning' Daphne Koller Why Structure Learning To learn model for new queries,

Learning' Probabilis2c' Graphical' BN'Structure' Models' Structure' Learning' Daphne Koller Why Structure Learning To learn model for new queries, when domain expertise is not perfect For structure discovery, when inferring network

752 views • 61 slides
Automatic Speech Recognition (CS753) Automatic Speech Recognition (CS753) Lecture 16: Language

Automatic Speech Recognition (CS753) Automatic Speech Recognition (CS753) Lecture 16: Language

Automatic Speech Recognition (CS753) Automatic Speech Recognition (CS753) Lecture 16: Language Models (Part III) Instructor: Preethi Jyothi Mar 16, 2017 Mid-semester feedback Thanks! Work out more examples esp. for topics that are

417 views • 25 slides
September 2019 Feedback and Presentation Policy 1 Introduction 1.1 At Lutley we believe that

September 2019 Feedback and Presentation Policy 1 Introduction 1.1 At Lutley we believe that

Feedback Policy September 2019 Feedback and Presentation Policy 1 Introduction 1.1 At Lutley we believe that effective feedback provides information to improve teaching and learning. We give our children regular feedback on their learning so

382 views • 8 slides
September 2018 Feedback and Presentation Policy 1 Introduction 1.1 At Lutley we believe that

September 2018 Feedback and Presentation Policy 1 Introduction 1.1 At Lutley we believe that

Feedback Policy September 2018 Feedback and Presentation Policy 1 Introduction 1.1 At Lutley we believe that effective feedback provides information to improve teaching and learning. We give our children regular feedback on their learning so

380 views • 8 slides
Student Evaluation of Learning and Feedback for Instructors Student Evaluation of Learning and

Student Evaluation of Learning and Feedback for Instructors Student Evaluation of Learning and

Student Evaluation of Learning and Feedback for Instructors Student Evaluation of Learning and Feedback for Instructors SELFI Initial USAT Charge Phase 1 USAT committee (2014 15) Adopt a new set of quantitative (Likert style) questions

610 views • 31 slides
Towards efficient automatic end-to-end learning Frank Hutter University of Freiburg, Germany

Towards efficient automatic end-to-end learning Frank Hutter University of Freiburg, Germany

Towards efficient automatic end-to-end learning Frank Hutter University of Freiburg, Germany Based on joint work with great students and collaborators (named throughout) Frank Hutter: Towards efficient automatic learning What will this partial

451 views • 22 slides
Learning is a never-ending process Tasks come and go, but learning is forever Learn more e ff

Learning is a never-ending process Tasks come and go, but learning is forever Learn more e ff

NeurIPS 2018 Tutorial on Automatic Machine Learning Learning to Learn Learning Learning Learning Learning Learning automl.org/events -> AutoML Tutorial -> Slides Frank Hutter Joaquin Vanschoren Eindhoven University of Technology

1.36k views • 40 slides
Module 14: Analyzing Queries Overview Queries That Use the AND Operator the OR

Module 14: Analyzing Queries Overview Queries That Use the AND Operator the OR

Module 14: Analyzing Queries Overview Queries That Use the AND Operator the OR Operator Join Operations Queries That Use the AND Operator Processing the AND Operator Returns rows that meet all conditions for every

231 views • 12 slides
Automatic student modelling for detecting learning style preferences in learning management

Automatic student modelling for detecting learning style preferences in learning management

Automatic student modelling for detecting learning style preferences in learning management systems Sabine Graf Silvia Rita Viola Kinshuk Vienna University of Technology Universita Politecnica delle Marche Athabasca University Vienna,

456 views • 21 slides
Learning agents Performance standard Critic Sensors Learning from Observations feedback

Learning agents Performance standard Critic Sensors Learning from Observations feedback

Learning agents Performance standard Critic Sensors Learning from Observations feedback Environment changes Chapter 18, Sections 13 Learning Performance element element knowledge learning goals experiments Problem generator

179 views • 5 slides
Learning agents Performance standard Critic Sensors Learning from Observations feedback

Learning agents Performance standard Critic Sensors Learning from Observations feedback

Learning agents Performance standard Critic Sensors Learning from Observations feedback Environment changes Chapter 18, Sections 13 Learning Performance element element knowledge learning goals experiments Problem generator

174 views • 6 slides
New Requirements Top-N/Bottom-N queries Interactive queries Decision making

New Requirements Top-N/Bottom-N queries Interactive queries Decision making

Lecture 13 Lecture 13 Advanced Query Processing CS5208 Advanced QP 1 New Requirements Top-N/Bottom-N queries Interactive queries Decision making queries Tolerant of errors approximate answers acceptable

675 views • 25 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
Seminar Report : Automatic Categorization of SQL-Query-Results Abhijith Kashyap

Seminar Report : Automatic Categorization of SQL-Query-Results Abhijith Kashyap

Seminar Report : Automatic Categorization of SQL-Query-Results Abhijith Kashyap rk39@cse.buffalo.edu March 24, 2008 Abstract huge result-set. Only a small portion of the result is of interest to the user, who Search queries on

429 views • 4 slides
Automatic Speech Recognition (CS753) Automatic Speech Recognition (CS753) Lecture 7: Hidden

Automatic Speech Recognition (CS753) Automatic Speech Recognition (CS753) Lecture 7: Hidden

Automatic Speech Recognition (CS753) Automatic Speech Recognition (CS753) Lecture 7: Hidden Markov Models (Part III) Instructor: Preethi Jyothi Aug 14, 2017 Recap: Learning HMM Parameters Given an HMM = ( A , B ) and an observation se-

514 views • 19 slides
APOLLO AUTOMATIC DETECTION AND DIAGNOSIS OF PERFORMANCE REGRESSIONS IN DATABASE SYSTEMS Jinho

APOLLO AUTOMATIC DETECTION AND DIAGNOSIS OF PERFORMANCE REGRESSIONS IN DATABASE SYSTEMS Jinho

APOLLO AUTOMATIC DETECTION AND DIAGNOSIS OF PERFORMANCE REGRESSIONS IN DATABASE SYSTEMS Jinho Jung , Hong Hu, Joy Arulraj, Taesoo Kim, Woonhak Kang* * APOLLO Holistic toolchain for debugging DBMS 1 AUTOMATICALLY FIND SQL QUERIES

843 views • 44 slides
Automatic Learning of a Morphological Model Theory and Unsupervised Approaches Unsupervised

Automatic Learning of a Morphological Model Theory and Unsupervised Approaches Unsupervised

Automatic Learning of a Morphological Model Theory and Unsupervised Approaches Unsupervised Learning - ToC Foundations Problem description General architecture Papers: Goldsmith 2001 and 2006 Goldsmith and Hu 2004

1.23k views • 43 slides
Matchbox automatic batching for imperative deep learning James Bradbury NVIDIA GTC, 2018/3/28

Matchbox automatic batching for imperative deep learning James Bradbury NVIDIA GTC, 2018/3/28

Matchbox automatic batching for imperative deep learning James Bradbury NVIDIA GTC, 2018/3/28 Roadmap Imperative deep learning How manual batching works Other tools for automatic batching The Matchbox approach: dispatch and

799 views • 30 slides
Growth Mindset, Behaviour & Feedback: A Learning Culture Rationale We have started the

Growth Mindset, Behaviour & Feedback: A Learning Culture Rationale We have started the

Growth Mindset, Behaviour & Feedback: A Learning Culture Rationale We have started the journey in Growth Mindset but are embedding it further within the school this year. Key to this development will be processes, language and feedback

235 views • 19 slides

More recommend