Full bibliography

Analogues of mental simulation and imagination in deep learning

Resource type
Author/contributor
Title
Analogues of mental simulation and imagination in deep learning
Abstract
Mental simulation—the capacity to imagine what will or what could be—is a salient feature of human cognition, playing a key role in a wide range of cognitive abilities. In artificial intelligence, the last few years have seen the development of methods which are analogous to mental models and mental simulation. This paper outlines recent methods in deep learning for constructing such models from data and learning to use them via reinforcement learning, and compares such approaches to human mental simulation. Model-based methods in deep learning can serve as powerful tools for building and scaling cognitive models. However, a number of challenges remain in matching the capacity of human mental simulation for efficiency, compositionality, generalization, and creativity.
Publication
Current Opinion in Behavioral Sciences
Volume
29
Pages
8-16
Date
October 1, 2019
Series
SI: 29: Artificial Intelligence (2019)
Journal Abbr
Current Opinion in Behavioral Sciences
DOI
10.1016/j.cobeha.2018.12.011
ISSN
2352-1546
Accessed
2019-10-10T19:15:54Z
Library Catalog
ScienceDirect
Citation
Hamrick, J. B. (2019). Analogues of mental simulation and imagination in deep learning. Current Opinion in Behavioral Sciences, 29, 8–16. https://doi.org/10.1016/j.cobeha.2018.12.011
BIOLOGY, NEUROSCIENCE & PSYCHOLOGY
Processing time: 0.03 seconds

Graph of references

(from Zotero to Gephi via Zotnet with this script)
Graph of references