Thinking Required
This addresses the foundational problem of understanding general learning principles in AI and cognitive science, but it is incremental as it reviews existing ideas rather than proposing new methods.
The paper reviews the theory of a single general-purpose learning algorithm that could explain mental operations, assuming an initial innate architecture and learned mental algorithms, by listing its ingredients from architectural and functional perspectives.
There exists a theory of a single general-purpose learning algorithm which could explain the principles its operation. It assumes the initial rough architecture, a small library of simple innate circuits which are prewired at birth. and proposes that all significant mental algorithms are learned. Given current understanding and observations, this paper reviews and lists the ingredients of such an algorithm from architectural and functional perspectives.