Learning, fast and slow

TL;DR

This paper surveys the neural mechanisms underlying fast and slow learning in animals, exploring how different representations and processes contribute to learning efficiency and variability across species.

Contribution

It provides a comparative analysis of hypotheses on neural representations and learning processes that differentiate fast from slow learning in animals.

Findings

Fast learning may depend on innate neural representations optimized for rapid adaptation.

Slow learning likely involves acquiring neural representations through experience via unsupervised learning.

Different neural mechanisms and representations may underlie the variability in learning speeds across species.

Abstract

Animals can learn efficiently from a single experience and change their future behavior in response. However, in other instances, animals learn very slowly, requiring thousands of experiences. Here I survey tasks involving fast and slow learning and consider some hypotheses for what differentiates the underlying neural mechanisms. It has been proposed that fast learning relies on neural representations that favor efficient Hebbian modification of synapses. These efficient representations may be encoded in the genome, resulting in a repertoire of fast learning that differs across species. Alternatively, the required neural representations may be acquired from experience through a slow process of unsupervised learning from the environment.