Reasoning algorithm based on importance sampling and neural circuit

Abstract

The invention provides a reasoning algorithm based on importance sampling and a neural circuit. The algorithm comprises the following steps that a Bayesian network corresponding to a Bayesian brain model to be reasoned is decomposed into a tree-like Bayesian network, wherein the tree-like Bayesian network comprises a highest layer father node and a plurality of son nodes; probabilistic reasoning is performed on the multiple son nodes of the tree-like Bayesian network sequentially from bottom to top, and a plurality of obtained reasoning results are uploaded layer by layer; according to the multiple reasoning results, the posterior probability of the highest layer father node is obtained, and a reasoning result of the Bayesian brain model to be reasoned is obtained according to the posterior probability of the highest layer father node. According to the reasoning algorithm, any Bayesian brain model can be reasoned, and the good universality is achieved.

Description

technical field [0001] The invention relates to the technical field of human brain science, in particular to a reasoning algorithm and neural circuit based on importance sampling. Background technique [0002] Many psychological and physiological experiments have shown that the cognitive process of the human brain is a probabilistic reasoning process, and the human brain can accept information representing uncertainty and process them. From a macro perspective, the Bayesian brain model can explain how the human brain perceives the world, and has been successfully applied to many aspects of cognitive science and human brain science, such as perception, cognition, sensory control and decision-making. But from a microscopic point of view, it is not clear how the neurons in the human brain perform Bayesian inference. [0003] At present, there have been some related research work. According to different methods of expressing probability, it can be divided into probability codin...

AI Technical Summary

Problems solved by technology

However, there are two problems in the current research: first, the scale is small, and the neural circuit implementation of simple problems is mainly studied. In fact, the problems encountered in daily life are extremely complex; second, it is task-based, and the current research is aimed at different Different neural circuits are designed by reasoning. The circuits are not universal and do not conform to the efficient working principle of the human brain.

Images