Stochastic-Based Pattern Recognition Analysis
This provides a faster pattern recognition method for navigation applications, though it appears incremental as it builds on existing stochastic logic and Bayesian techniques.
The authors applied stochastic logic to probabilistic pattern recognition, creating a parallel Bayesian comparison system that was orders of magnitude faster than processor-based solutions for a navigation problem.
In this work we review the basic principles of stochastic logic and propose its application to probabilistic-based pattern-recognition analysis. The proposed technique is intrinsically a parallel comparison of input data to various pre-stored categories using Bayesian techniques. We design smart pulse-based stochastic-logic blocks to provide an efficient pattern recognition analysis. The proposed rchitecture is applied to a specific navigation problem. The resulting system is orders of magnitude faster than processor-based solutions.