Inductive Models for Artificial Intelligence Systems are Insufficient without Good Explanations

TL;DR

The paper argues that inductive ML models excel at fitting data but lack explanatory depth, limiting generalization to unseen scenarios. It juxtaposes induction with scientific explanation, drawing on Popper and Deutsch to define criteria for robust theories (falsifiability and hard-to-vary conjectures) and to critique purely predictive approaches. It contends that current explainable-AI efforts do not guarantee meaningful explanations and that a shift toward models that expose underlying mechanisms and cross-distribution extrapolation is needed. The practical impact is a call to develop AI systems that offer reliable explanations, not just accurate predictions, to improve trust, safety, and generalizability.

Abstract

This paper discusses the limitations of machine learning (ML), particularly deep artificial neural networks (ANNs), which are effective at approximating complex functions but often lack transparency and explanatory power. It highlights the `problem of induction' : the philosophical issue that past observations may not necessarily predict future events, a challenge that ML models face when encountering new, unseen data. The paper argues for the importance of not just making predictions but also providing good explanations, a feature that current models often fail to deliver. It suggests that for AI to progress, we must seek models that offer insights and explanations, not just predictions.