A High-Level Model of Neocortical Feedback Based on an Event Window Segmentation Algorithm

TL;DR

This paper extends an event window segmentation algorithm to predict future events and constructs a high-level neocortical hierarchy model that learns hierarchical patterns and predictions from event streams.

Contribution

It introduces a novel hierarchical model of neocortical feedback based on an extended event window segmentation algorithm with predictive capabilities.

Findings

Hierarchical pattern recognition improves with higher levels.

Predictions from higher levels reinforce lower-level predictions.

The model demonstrates a simplified neocortical processing scheme.

Abstract

The author previously presented an event window segmentation (EWS) algorithm [5] that uses purely statistical methods to learn to recognize recurring patterns in an input stream of events. In the following discussion, the EWS algorithm is first extended to make predictions about future events. Next, this extended algorithm is used to construct a high-level, simplified model of a neocortical hierarchy. An event stream enters at the bottom of the hierarchy, and drives processing activity upward in the hierarchy. Successively higher regions in the hierarchy learn to recognize successively deeper levels of patterns in these events as they propagate from the bottom of the hierarchy. The lower levels in the hierarchy use the predictions from the levels above to strengthen their own predictions. A C++ source code listing of the model implementation and test program is included as an appendix.