Analogues of mental simulation and imagination in deep learning
| Autor: | Jessica B. Hamrick |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Cognitive science
Computer science Principle of compositionality business.industry Cognitive Neuroscience Deep learning media_common.quotation_subject 05 social sciences Cognition Creativity 050105 experimental psychology 03 medical and health sciences Behavioral Neuroscience Psychiatry and Mental health 0302 clinical medicine Salient Generalization (learning) Feature (machine learning) Reinforcement learning 0501 psychology and cognitive sciences Artificial intelligence business 030217 neurology & neurosurgery media_common |
| Zdroj: | Current Opinion in Behavioral Sciences. 29:8-16 |
| ISSN: | 2352-1546 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect