Discussion on Mechanical Learning and Learning Machine

TL;DR

This paper explores the concept of mechanical learning, a simple rule-based system that learns from data, contrasting it with traditional machine learning, and proposes two research directions for further development.

Contribution

It clarifies the principles of mechanical learning and introduces a framework for future research, emphasizing simplicity over complexity in learning systems.

Findings

Mechanical learning is based on fixed, simple rules.

A framework for studying mechanical learning is proposed.

Two research directions are outlined for advancing mechanical learning.

Abstract

Mechanical learning is a computing system that is based on a set of simple and fixed rules, and can learn from incoming data. A learning machine is a system that realizes mechanical learning. Importantly, we emphasis that it is based on a set of simple and fixed rules, contrasting to often called machine learning that is sophisticated software based on very complicated mathematical theory, and often needs human intervene for software fine tune and manual adjustments. Here, we discuss some basic facts and principles of such system, and try to lay down a framework for further study. We propose 2 directions to approach mechanical learning, just like Church-Turing pair: one is trying to realize a learning machine, another is trying to well describe the mechanical learning.