Context sequence theory: a common explanation for multiple types of learning

TL;DR

This paper introduces the context sequence theory, a neuroscience-inspired framework aiming to unify explanations for various mammalian learning types and inspire new machine learning models.

Contribution

It proposes a novel theory based on neuroscience to unify multiple mammalian learning processes and guide machine learning model development.

Findings

Provides a common explanatory framework for mammalian learning types

Suggests new directions for machine learning model design

Bridges neuroscience principles with machine learning

Abstract

Although principles of neuroscience like reinforcement learning, visual perception and attention have been applied in machine learning models, there is a huge gap between machine learning and mammalian learning. Based on the advances in neuroscience, we propose the context sequence theory to give a common explanation for multiple types of learning in mammals and hope that can provide a new insight into the construct of machine learning models.