Bayesian Program Learning and Concept Induction

reportActive / Technical Report | Accession Number: AD1096503 | Open PDF

Abstract:

A long-standing dream in computing has been to build machines that learn like a child Turing 1950 that grow into all the kinds and forms of knowledge that human adults do, starting from much less. At a minimum, any such learning system must be able to acquire many different kinds of expertise. Every child becomes an expert in natural language, motor control, intuitive physics and social interaction, and many will grow into adults with specialized expertise in cooking, calculus, tennis, drawing pictures, or writing software. Despite great advances, artificial intelligence AI is still far from acquiring human-like expertise in any of these domains let alone all of them, as a person can.

Author(s):
Tenenbaum, Josh
Author Organization(s):
Massachusetts Institute of Technology Cambridge United States
Descriptive Note:
Technical Report,15 Dec 2015,14 Feb 2018
Pagination:
0012

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution:
Approved For Public Release
Distribution Statement:
Approved For Public Release;

RECORD

Collection: TR
Identifying Numbers
Report Number(s):
AFRL-AFOSR-VA-TR-2019-0280
Monitor Series:
AFRL-AFOSR-VA-TR-2019-0280
 Subject Terms
Joint Capability Areas:
JCA_1.2.6_Concepts; JCA_5_Command and Control; JCA_5.5.2_Task; JCA_5.5_Direct; JCA_1.3.1_Personnel and Family Support; JCA_5.3_Planning; JCA_1.2.1_Training; JCA_5.2.2_Develop Knowledge and Situational Awareness; JCA_5.2_Understand
Modernization Areas:
AI and Machine Learning
Communities of Interest:
Autonomy
Descriptor(s):
probability, statistical inference, machine learning, artificial intelligence, bayesian networks, artificial intelligence computing, computer programming, pattern recognition
Field(s)/Group(s):
Statistics and Probability, Cybernetics
Keyword(s):
Bayesian Induction, Concept Formulation, A Priori Knowledge, Probabilistic Inference
Report Date:
2019 Sep 21
Creation Date:
2020 Apr 23