Enabling Compositional Generalization of AI Systems
A vital aspect of human intelligence is the ability to compose increasingly complex concepts out of simpler ideas, enabling both rapid learning and adaptation of knowledge. Despite their impressive performance, current AI systems fall short in this area and are often unable to solve tasks that fall...
Main Author: | Li, Shuang |
---|---|
Other Authors: | Torralba, Antonio |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2023
|
Online Access: | https://hdl.handle.net/1721.1/152678 https://orcid.org/0000-0002-7276-5032 |
Similar Items
-
AI-enabled future crime
by: M. Caldwell, et al.
Published: (2020-08-01) -
AI-Enabled Monitoring, Diagnosis & Prognosis
by: Ruqiang Yan, et al.
Published: (2021-07-01) -
AI-Enabled Trust in Distributed Networks
by: Zhiqi Li, et al.
Published: (2023-01-01) -
Baba is AI: A Grounded Benchmark for
Compositional Generalization in Dynamic Rule
Systems
by: Jens, Meagan
Published: (2023) -
Obstacle and collision avoidance system for AI-enabled multi-robot system
by: Malik, Khalif Adam
Published: (2019)