Artificial Learning in Artificial Memories

TL;DR

This paper proposes a memory refinement method that enables artificial systems to learn action sequences through repetition, allowing automatic execution without CPU involvement, mimicking human learning processes.

Contribution

It introduces a novel memory refinement approach that facilitates automatic sequence execution, advancing artificial learning capabilities.

Findings

Memory refinement detects repeated action sequences

Sequences are executed automatically without CPU

Approach mimics human learning processes

Abstract

Memory refinements are designed below to detect those sequences of actions that have been repeated a given number n. Subsequently such sequences are permitted to run without CPU involvement. This mimics human learning. Actions are rehearsed and once learned, they are performed automatically without conscious involvement.