Short-term Cognitive Networks, Flexible Reasoning and Nonsynaptic Learning

TL;DR

This paper introduces Short-term Cognitive Networks, a flexible neural network model that enhances reasoning and learning from knowledge structures, addressing limitations of Fuzzy Cognitive Maps with a nonsynaptic learning algorithm and stopping criteria.

Contribution

The paper proposes a new neural network system with unconstrained weights and a nonsynaptic learning algorithm, improving reasoning capabilities and prediction accuracy.

Findings

Effective in handling external knowledge structures

Improves prediction horizon over traditional FCMs

Prevents unnecessary learning iterations

Abstract

While the machine learning literature dedicated to fully automated reasoning algorithms is abundant, the number of methods enabling the inference process on the basis of previously defined knowledge structures is scanter. Fuzzy Cognitive Maps (FCMs) are neural networks that can be exploited towards this goal because of their flexibility to handle external knowledge. However, FCMs suffer from a number of issues that range from the limited prediction horizon to the absence of theoretically sound learning algorithms able to produce accurate predictions. In this paper, we propose a neural network system named Short-term Cognitive Networks that tackle some of these limitations. In our model weights are not constricted and may have a causal nature or not. As a second contribution, we present a nonsynaptic learning algorithm to improve the network performance without modifying the previously defined weights. Moreover, we derive a stop condition to prevent the learning algorithm from iterating without decreasing the simulation error.