The Cortical Graph (COGRAPH) Project an Investigation into the Representation of Complex Contextual Relationships Based on the Structure of Cerebral Cortex
Abstract
A key element of any kind of intelligent computing is the management and recognition of sensor data. And although applications are being studied for a range of sensor modalities, the most complicated and perhaps most pervasive is that of analyzing and understanding moving images. The purpose of the research described here is to explore neural inspired algorithms, loosely based on cortical structures, as new approaches to capturing, representing, and then performing inference over higher order structure of features in a still or moving image. The approach is to study the use of hierarchical, modular, sparsely distributed structures loosely based on the HTM family of algorithms.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 15, 2019
- Accession Number
- AD1065748
Entities
People
- Dan Hammerstrom
Organizations
- Portland State University