A critique of pure learning and what artificial neural networks can learn from animal brains

Zador, A. M. (August 2019) A critique of pure learning and what artificial neural networks can learn from animal brains. Nat Commun, 10 (1). p. 3770. ISSN 2041-1723

[img]
Preview
PDF
2019.Zador.ArtificialNeuralNetworks.pdf - Published Version

Download (475kB) | Preview
URL: https://www.ncbi.nlm.nih.gov/pubmed/31434893
DOI: 10.1038/s41467-019-11786-6

Abstract

Artificial neural networks (ANNs) have undergone a revolution, catalyzed by better supervised learning algorithms. However, in stark contrast to young animals (including humans), training such networks requires enormous numbers of labeled examples, leading to the belief that animals must rely instead mainly on unsupervised learning. Here we argue that most animal behavior is not the result of clever learning algorithms-supervised or unsupervised-but is encoded in the genome. Specifically, animals are born with highly structured brain connectivity, which enables them to learn very rapidly. Because the wiring diagram is far too complex to be specified explicitly in the genome, it must be compressed through a "genomic bottleneck". The genomic bottleneck suggests a path toward ANNs capable of rapid learning.

Item Type: Paper
Subjects: organism description > animal behavior
organs, tissues, organelles, cell types and functions > tissues types and functions > neural networks
CSHL Authors:
Communities: CSHL labs > Zador lab
Depositing User: Matthew Dunn
Date: 21 August 2019
Date Deposited: 26 Aug 2019 14:56
Last Modified: 18 Dec 2019 18:53
PMCID: PMC6704116
Related URLs:
URI: https://repository.cshl.edu/id/eprint/38307

Actions (login required)

Administrator's edit/view item Administrator's edit/view item
CSHL HomeAbout CSHLResearchEducationNews & FeaturesCampus & Public EventsCareersGiving