A Brain-Inspired Causal Reasoning Model Based on Spiking Neural Networks

Hongjian Fang, Yi Zeng

Abstract: In today's field of artificial intelligence, the plausibility of neural networks still lacks breakthrough. We believe one reason is that the current deep neural network method based on the framework of statistical learning, in essence, only uses the correlation between the data to make predictions, different from human beings who complete reasoning and decision-making by invariably induce the causality between propositions. To solve this problem, previous researchers have proposed some causal reasoning approaches based on the causal graphs. Inspired by the human brain, we propose Causal Reasoning Spiking Neural Network(CRSNN) to implement the causal reasoning with STDP learning rule and population coding mechanism. After the verification experiment in the basic case, we show the possibility of implementation causal reasoning with SNN. As far as we know, this is the first time that SNN is used to complete causal reasoning tasks, which is an essential topic both in cognitive neuroscience and artificial intelligence.