Post-Selections in AI and How to Avoid Them
This addresses methodological issues in AI research that could affect the reliability of reported results, though it appears incremental in its critique of existing practices.
The paper identifies a rarely reported stage called Post-Selection in AI experiments, which can lead to misleading results due to protocol flaws, and proposes developmental networks as a solution to avoid these pitfalls by automatically discovering context-rules under specific learning conditions.
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.