Published on Sun Sep 21 2014

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

Jerry R. Van Aken

An event window segmentation (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 hierarchy. An event stream enters at the bottom of the hierarchy and drives processing activity upward in the hierarchy.

0
0
0
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.

Thu Dec 29 2016
Machine Learning
The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process
Some event types are stochastically excited or inhibited by patterns in the sequence of previous events. Discovering such patterns can help us predict which type of event will happen next and when. We construct a neurally self-modulating multivariate point process.
1
3
6
Fri May 30 2014
Neural Networks
ELM Solutions for Event-Based Systems
Most engineered systems use signals that are continuous in time. Events, like Dirac grotesquedelta functions, have no meaningful time duration. In this domain, signal processing requires responses to spatio-temporal patterns of events.
0
0
0
Thu Mar 13 2014
Neural Networks
Controlling Recurrent Neural Networks by Conceptors
The human brain is a dynamical system whose extremely complex sensor-driven processes give rise to conceptual, logical cognition. Here I propose a mechanism of neurodynamical organization, called conceptors, which unites nonlinear dynamics with basic principles of conceptual abstraction and logic.
0
0
0
Thu Apr 02 2020
Neural Networks
Neuronal Sequence Models for Bayesian Online Inference
Sequential neuronal activity underlies a wide range of processes in the brain. Neuroscientific evidence for neuronal sequences has been reported in domains as diverse as perception, motor control, speech, spatial navigation andmemory.
0
0
0
Wed Oct 11 2017
Neural Networks
Discrete Event, Continuous Time RNNs
We investigate recurrent neural network architectures for event-sequence processing. Event sequences are characterized by discrete observations stamped with continuous-valued times of occurrence. Event time-stamps drive decay dynamics of the CT-GRU, whereas the GRU serves as generic additional inputs.
0
0
0
Thu Jul 11 2019
Machine Learning
Spatiotemporal Local Propagation
This paper proposes an in-depth re-thinking of neural computation. The scheme, which is referred to as SpatioTemporal Local Propagation (STLP), is local in both space and time. The theory holds for horriblyneural networks that are also based on any digraph.
0
0
0