The Convergence of AI code and Cortical Functioning -- a Commentary

Neural nets, one of the oldest architectures for AI programming, are loosely based on biological neurons and their properties. Recent work on language applications has made the AI code closer to biological reality in several ways. This commentary examines this convergence and, in light of what is known of neocortical structure, addresses the question of whether "general AI" looks attainable with these tools. One of the earliest ideas for programming Artificial Intelligence was to imitate neurons and their connectivity with neural nets. In the turbulent boom and bust evolution of AI, this remained a theme with strong adherents, but it fell out of the mainstream until around 2010 when these ideas were implemented with really huge datasets and really fast computers. The field of AI has now had a decade of tremendous progress in which neural nets, along with some major improvements, have been the central character. The purpose of this post is to describe the further parallels between the software implementation of AI and the instantiation of cognitive intelligence in mammalian brains. I conjecture that, for better or for worse, all future instances of artificial intelligence will be driven to use these algorithms even though they are opaque and resist simple explanations of why they do what they do. This commentary follows my blog post here. Such a function is always diagrammed as a set of layers, with functions φ computing the next higher layer from the layer below and the running value after each composition being called the "activity" x The components of these activities are called "units", as these are supposed to correspond to neurons in the biological interpretation.