Show simple item record

dc.contributor.advisorTomaso Poggio.en_US
dc.contributor.authorPrinster, Ryan(Ryan T.)en_US
dc.contributor.otherMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.en_US
dc.date.accessioned2020-11-23T17:39:16Z
dc.date.available2020-11-23T17:39:16Z
dc.date.copyright2019en_US
dc.date.issued2019en_US
dc.identifier.urihttps://hdl.handle.net/1721.1/128571
dc.descriptionThis electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.en_US
dc.descriptionThesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, September, 2019en_US
dc.descriptionCataloged from student-submitted PDF of thesis.en_US
dc.descriptionIncludes bibliographical references (pages 67-69).en_US
dc.description.abstractMany of the predominant learning paradigms in modern machine learning techniques are inspired by biology. Deep networks are inspired by the neurons in the brain, and reinforcement learning was originally inspired by operant conditioning in cognitive science. However, there are still signicant gaps between artifical and biological models of intelligence. One notable difference is sample eciency - animals, in particular humans, are able to understand concepts and solve tasks with only a few demonstrations, whereas artifical agents take millions of examples and make just as many mistakes. This paper aims to quantify the raw difference in sample efficiency, accounting for the signicant priors held by biological agents. We do this by designing a suite of tasks that must be solved by both agents, in which each task requires a significantly dierent aspect of general intelligence to be solved. We train artifical and biological agents on said tasks after initial learning stages to control for significant priors, and finally examine and compare the quality and efficiency of learning in these tasks, such that we might understand the relationship between the sample eciency of biological and artifical agents in general learning environments.en_US
dc.description.statementofresponsibilityby Ryan Prinster.en_US
dc.format.extent69 pagesen_US
dc.language.isoengen_US
dc.publisherMassachusetts Institute of Technologyen_US
dc.rightsMIT 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.en_US
dc.rights.urihttp://dspace.mit.edu/handle/1721.1/7582en_US
dc.subjectElectrical Engineering and Computer Science.en_US
dc.titleOn sample eciency in artifical and biological agentsen_US
dc.typeThesisen_US
dc.description.degreeM. Eng.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.identifier.oclc1220875111en_US
dc.description.collectionM.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Scienceen_US
dspace.imported2020-11-23T17:39:15Zen_US
mit.thesis.degreeMasteren_US
mit.thesis.departmentEECSen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record