.png){kind=icon}
.png){kind=icon}
Return
The overfitted brain hypothesis
.png){kind=icon}
OA
AI
DOI：10.1016/j.patter.2021.100268.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
What is the purpose of dreaming? Many scientists have postulated a role for dreaming in learning, often with the aim of improving generative models. In this issue of Patterns, Erik Hoel proposes a novel hypothesis, namely, that dreaming provides a means to reduce overfitting. This hypothesis is interesting both for neuroscience and for the development of new machine-learning systems.
Keywords:
ALGORITHM
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.4
Papers:
938
Citations:
3.6K