Unified Inductive Logic: From Formal Learning to Statistical Inference to Supervised Learning
This work addresses foundational issues in inductive logic for researchers in philosophy, statistics, and machine learning, but appears incremental as it builds on existing frameworks.
The paper tackles the problem of unifying different approaches to inductive reasoning by developing a Peircean alternative to Carnapian inductive logic, aiming to integrate formal learning theory, statistics, and supervised learning under a single principle.
While the traditional conception of inductive logic is Carnapian, I develop a Peircean alternative and use it to unify formal learning theory, statistics, and a significant part of machine learning: supervised learning. Some crucial standards for evaluating non-deductive inferences have been assumed separately in those areas, but can actually be justified by a unifying principle.