{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/130184"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/130184","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Algorithms for learning to induce programs","abstract":"The future of machine learning should have a knowledge representation that supports, at a minimum, several features: Expressivity, interpretability, the potential for reuse by both humans and machines, while also enabling sample-efficient generalization. Here we argue that programs-i.e., source code-are a knowledge representation which can contribute to the project of capturing these elements of intelligence. This research direction however requires new program synthesis algorithms which can induce programs solving a range of AI tasks. This program induction challenge confronts two primary obstacles: the space of all programs is infinite, so we need a strong inductive bias or prior to steer us toward the correct programs; and even if we have that prior, effectively searching through the vast combinatorial space of all programs is generally intractable. We introduce algorithms that learn to induce programs, with the goal of addressing these two primary obstacles. Focusing on case studies in vision, computational linguistics, and learning-to-learn, we develop an algorithmic toolkit for learning inductive biases over programs as well as learning to search for programs, drawing on probabilistic, neural, and symbolic methods. Together this toolkit suggests ways in which program induction can contribute to AI, and how we can use learning to improve program synthesis technologies.","abstract_html":"The future of machine learning should have a knowledge representation that supports, at a minimum, several features: Expressivity, interpretability, the potential for reuse by both humans and machines, while also enabling sample-efficient generalization. Here we argue that programs-i.e., source code-are a knowledge representation which can contribute to the project of capturing these elements of intelligence. This research direction however requires new program synthesis algorithms which can induce programs solving a range of AI tasks. This program induction challenge confronts two primary obstacles: the space of all programs is infinite, so we need a strong inductive bias or prior to steer us toward the correct programs; and even if we have that prior, effectively searching through the vast combinatorial space of all programs is generally intractable. We introduce algorithms that learn to induce programs, with the goal of addressing these two primary obstacles. Focusing on case studies in vision, computational linguistics, and learning-to-learn, we develop an algorithmic toolkit for learning inductive biases over programs as well as learning to search for programs, drawing on probabilistic, neural, and symbolic methods. Together this toolkit suggests ways in which program induction can contribute to AI, and how we can use learning to improve program synthesis technologies.","abstract_has_math":false,"creators":["Ellis, Kevin,Ph. D.(Kevin M.)Massachusetts Institute of Technology."],"institution":"Massachusetts Institute of Technology","degree_name":"Doctoral","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences","school":null,"contributors":[],"advisors":["Joshua B. Tenenbaum and Armando Solar-Lezama."],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020","date_published":"2020","updated_at":"2026-07-22T22:20:59Z","subjects":["Brain and Cognitive Sciences."],"languages":["eng"],"rights":["MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/130184","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Joshua B. Tenenbaum and Armando Solar-Lezama."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences","Brain"]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences."]},{"key":"dc:creator","label":"Author","values":["Ellis, Kevin,Ph. D.(Kevin M.)Massachusetts Institute of Technology."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2021-03-22T17:05:57Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2021-03-22T17:05:57Z"]},{"key":"dc:date.issued","label":"Date","values":["2020"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctoral"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Brain and Cognitive Sciences."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/130184"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis: Ph. D. in Cognitive Science, Massachusetts Institute of Technology, Department of Brain and Cognitive Sciences, September, 2020","Cataloged from student-submitted PDF version of thesis.","Includes bibliographical references (pages 213-224)."]},{"key":"dc:description.abstract","label":"Abstract","values":["The future of machine learning should have a knowledge representation that supports, at a minimum, several features: Expressivity, interpretability, the potential for reuse by both humans and machines, while also enabling sample-efficient generalization. Here we argue that programs-i.e., source code-are a knowledge representation which can contribute to the project of capturing these elements of intelligence. This research direction however requires new program synthesis algorithms which can induce programs solving a range of AI tasks. This program induction challenge confronts two primary obstacles: the space of all programs is infinite, so we need a strong inductive bias or prior to steer us toward the correct programs; and even if we have that prior, effectively searching through the vast combinatorial space of all programs is generally intractable. We introduce algorithms that learn to induce programs, with the goal of addressing these two primary obstacles. Focusing on case studies in vision, computational linguistics, and learning-to-learn, we develop an algorithmic toolkit for learning inductive biases over programs as well as learning to search for programs, drawing on probabilistic, neural, and symbolic methods. Together this toolkit suggests ways in which program induction can contribute to AI, and how we can use learning to improve program synthesis technologies."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph. D. in Cognitive Science"]},{"key":"dc:title","label":"Title","values":["Algorithms for learning to induce programs"]}]}],"canonical_facts":{"dc:contributor.advisor":["Joshua B. Tenenbaum and Armando Solar-Lezama."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences","Brain"],"dc:contributor.other":["Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences."],"dc:creator":["Ellis, Kevin,Ph. D.(Kevin M.)Massachusetts Institute of Technology."],"dc:date.accessioned":["2021-03-22T17:05:57Z"],"dc:date.available":["2021-03-22T17:05:57Z"],"dc:date.issued":["2020"],"dc:description":["Thesis: Ph. D. in Cognitive Science, Massachusetts Institute of Technology, Department of Brain and Cognitive Sciences, September, 2020","Cataloged from student-submitted PDF version of thesis.","Includes bibliographical references (pages 213-224)."],"dc:description.abstract":["The future of machine learning should have a knowledge representation that supports, at a minimum, several features: Expressivity, interpretability, the potential for reuse by both humans and machines, while also enabling sample-efficient generalization. Here we argue that programs-i.e., source code-are a knowledge representation which can contribute to the project of capturing these elements of intelligence. This research direction however requires new program synthesis algorithms which can induce programs solving a range of AI tasks. This program induction challenge confronts two primary obstacles: the space of all programs is infinite, so we need a strong inductive bias or prior to steer us toward the correct programs; and even if we have that prior, effectively searching through the vast combinatorial space of all programs is generally intractable. We introduce algorithms that learn to induce programs, with the goal of addressing these two primary obstacles. Focusing on case studies in vision, computational linguistics, and learning-to-learn, we develop an algorithmic toolkit for learning inductive biases over programs as well as learning to search for programs, drawing on probabilistic, neural, and symbolic methods. Together this toolkit suggests ways in which program induction can contribute to AI, and how we can use learning to improve program synthesis technologies."],"dc:description.degree":["Ph. D. in Cognitive Science"],"dc:identifier.uri":["https://hdl.handle.net/1721.1/130184"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Brain and Cognitive Sciences."],"dc:title":["Algorithms for learning to induce programs"],"dc:type":["Thesis"],"thesis:degree_name":["Doctoral"]},"updated_at":"2026-07-22T22:20:59Z"}