A New Approach for Knowledge Generation Using Active Inference

TL;DR

This paper introduces a novel brain-inspired model based on the free energy principle that generates various types of knowledge through active inference and probabilistic computation, aiming to enhance cognitive and AI systems.

Contribution

The study proposes a comprehensive, unsupervised model capable of generating declarative, procedural, and conditional knowledge using active inference and probabilistic mathematics.

Findings

Model effectively generates multiple knowledge types.

Capable of updating and generating new concepts.

Utilizes active inference for procedural and conditional knowledge.

Abstract

There are various models proposed on how knowledge is generated in the human brain including the semantic networks model. Although this model has been widely studied and even computational models are presented, but, due to various limits and inefficiencies in the generation of different types of knowledge, its application is limited to semantic knowledge because of has been formed according to semantic memory and declarative knowledge and has many limits in explaining various procedural and conditional knowledge. Given the importance of providing an appropriate model for knowledge generation, especially in the areas of improving human cognitive functions or building intelligent machines, improving existing models in knowledge generation or providing more comprehensive models is of great importance. In the current study, based on the free energy principle of the brain, is the researchers proposed a model for generating three types of declarative, procedural, and conditional knowledge. While explaining different types of knowledge, this model is capable to compute and generate concepts from stimuli based on probabilistic mathematics and the action-perception process (active inference). The proposed model is unsupervised learning that can update itself using a combination of different stimuli as a generative model can generate new concepts of unsupervised received stimuli. In this model, the active inference process is used in the generation of procedural and conditional knowledge and the perception process is used to generate declarative knowledge.