A Repeated Signal Difference for Recognising Patterns

TL;DR

This paper introduces a novel mechanism for pattern recognition based on oscillating upper bounds of ensemble values, enabling detection and measurement of repeating pattern sequences through feedback-driven oscillations.

Contribution

It proposes a new feedback-based method that captures pattern sequences by oscillating bounds, improving recognition of repeating patterns over time.

Findings

Oscillating bounds effectively recognize repeating pattern sequences.

Changing sequence order alters the oscillation values, enabling pattern differentiation.

The method provides measurable indicators for pattern recognition.

Abstract

This paper describes a new mechanism that might help with defining pattern sequences, by the fact that it can produce an upper bound on the ensemble value that can persistently oscillate with the actual values produced from each pattern. With every firing event, a node also receives an on/off feedback switch. If the node fires, then it sends a feedback result depending on the input signal strength. If the input signal is positive or larger, it can store an 'on' switch feedback for the next iteration. If the signal is negative or smaller, it can store an 'off' switch feedback for the next iteration. If the node does not fire, then it does not affect the current feedback situation and receives the switch command produced by the last active pattern event for the same neuron. The upper bound therefore also represents the largest or most enclosing pattern set and the lower value is for the actual set of firing patterns. If the pattern sequence repeats, it will oscillate between the two values, allowing them to be recognised and measured more easily, over time. Tests show that changing the sequence ordering produces different value sets, which can also be measured.