Post-Selections in AI and How to Avoid Them

TL;DR

This paper highlights the often-overlooked issue of post-selection bias in AI experiments, critiques current protocols, and proposes developmental errors as a new metric to ensure transparency and robustness in AI training.

Contribution

It introduces a comprehensive analysis of post-selection flaws in AI research and proposes developmental errors and developmental networks as novel solutions to improve transparency and reliability.

Findings

Post-selection biases can mislead AI experiment results.

Developmental networks inherently avoid post-selection pitfalls.

Current protocols often lack transparency in post-selection reporting.

Abstract

Neural network based Artificial Intelligence (AI) has reported increasing scales in experiments. However, this paper raises a rarely reported stage in such experiments called Post-Selection alter the reader to several possible protocol flaws that may result in misleading results. All AI methods fall into two broad schools, connectionist and symbolic. The Post-Selection fall into two kinds, Post-Selection Using Validation Sets (PSUVS) and Post-Selection Using Test Sets (PSUTS). Each kind has two types of post-selectors, machines and humans. The connectionist school received criticisms for its "black box" and now the Post-Selection; but the seemingly "clean" symbolic school seems more brittle because of its human PSUTS. This paper first presents a controversial view: all static "big data" are non-scalable. We then analyze why error-backprop from randomly initialized weights suffers from severe local minima, why PSUVS lacks cross-validation, why PSUTS violates well-established protocols, and why every paper involved should transparently report the Post-Selection stage. To avoid future pitfalls in AI competitions, this paper proposes a new AI metrics, called developmental errors for all networks trained, under Three Learning Conditions: (1) an incremental learning architecture (due to a "big data" flaw), (2) a training experience and (3) a limited amount of computational resources. Developmental Networks avoid Post-Selections because they automatically discover context-rules on the fly by generating emergent Turing machines (not black boxes) that are optimal in the sense of maximum-likelihood across lifetime, conditioned on the Three Learning Conditions.