Discussion on Mechanical Learning and Learning Machine
It addresses the problem of simplifying learning systems for researchers by proposing a foundational framework, but it is incremental as it builds on existing concepts without new empirical results.
The paper introduces mechanical learning as a computing system based on simple, fixed rules that learns from data, contrasting it with complex machine learning, and proposes a framework with two directions for further study.
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.