AI Centered on Scene Fitting and Dynamic Cognitive Network

TL;DR

This paper proposes a scene fitting-centered AI system with a Dynamic Cognitive Network model that unifies knowledge representation and processing, aiming to enhance AI's adaptability and reasoning capabilities across different domains.

Contribution

It introduces the Dynamic Cognitive Network (DC Net) model and a comprehensive framework for scene-based AI, emphasizing unified knowledge representation, multi-layer network structures, and cognitive probability models.

Findings

Design of a two-dimensional multi-layer network structure for AI processing

Development of a cognitive probability model for scene understanding

Proposal of an omnidirectional network matching-growth algorithm

Abstract

This paper briefly analyzes the advantages and problems of AI mainstream technology and puts forward: To achieve stronger Artificial Intelligence, the end-to-end function calculation must be changed and adopt the technology system centered on scene fitting. It also discusses the concrete scheme named Dynamic Cognitive Network model (DC Net). Discussions : The knowledge and data in the comprehensive domain are uniformly represented by using the rich connection heterogeneous Dynamic Cognitive Network constructed by conceptualized elements; A network structure of two dimensions and multi layers is designed to achieve unified implementation of AI core processing such as combination and generalization; This paper analyzes the implementation differences of computer systems in different scenes, such as open domain, closed domain, significant probability and non-significant probability, and points out that the implementation in open domain and significant probability scene is the key of AI, and a cognitive probability model combining bidirectional conditional probability, probability passing and superposition, probability col-lapse is designed; An omnidirectional network matching-growth algorithm system driven by target and probability is designed to realize the integration of parsing, generating, reasoning, querying, learning and so on; The principle of cognitive network optimization is proposed, and the basic framework of Cognitive Network Learning algorithm (CNL) is designed that structure learning is the primary method and parameter learning is the auxiliary. The logical similarity of implementation between DC Net model and human intelligence is analyzed in this paper.