The SP theory of intelligence: distinctive features and advantages

Abstract

This paper highlights distinctive features of the "SP theory of intelligence" and its apparent advantages compared with some AI-related alternatives. Distinctive features and advantages are: simplification and integration of observations and concepts; simplification and integration of structures and processes in computing systems; the theory is itself a theory of computing; it can be the basis for new architectures for computers; information compression via the matching and unification of patterns and, more specifically, via multiple alignment, is fundamental; transparency in the representation and processing of knowledge; the discovery of 'natural' structures via information compression (DONSVIC); interpretations of mathematics; interpretations in human perception and cognition; and realisation of abstract concepts in terms of neurons and their inter-connections ("SP-neural"). These things relate to AI-related alternatives: minimum length encoding and related concepts; deep learning in neural networks; unified theories of cognition and related research; universal search; Bayesian networks and more; pattern recognition and vision; the analysis, production, and translation of natural language; Unsupervised learning of natural language; exact and inexact forms of reasoning; representation and processing of diverse forms of knowledge; IBM's Watson; software engineering; solving problems associated with big data, and in the development of intelligence in autonomous robots. In conclusion, the SP system can provide a firm foundation for the long-term development of AI, with many potential benefits and applications. It may also deliver useful results on relatively short timescales. A high-parallel, open-source version of the SP machine, derived from the SP computer model, would be a means for researchers everywhere to explore what can be done with the system, and to create new versions of it.

References in corpus (17)

• Deep Learning in Neural Networks: An Overview
• Sequence to Sequence Learning with Neural Networks
• Intriguing properties of neural networks
• Text Understanding from Scratch
• Medical diagnosis as pattern recognition in a framework of information compression by multiple alignment, unification and search
• Big Neural Networks Waste Capacity
• Big data and the SP theory of intelligence
• Towards an Intelligent Database System Founded on the SP Theory of Computing and Cognition
• Application of the SP theory of intelligence to the understanding of natural vision and the development of computer vision
• Sketch-a-Net that Beats Humans
• Autonomous robots and the SP theory of intelligence
• Unifying Computing and Cognition: The SP Theory and its Applications
• The SP theory of intelligence: an overview
• The SP theory of intelligence: benefits and applications
• Semantic Amodal Segmentation
• Information Compression, Intelligence, Computing, and Mathematics
• Proposal for the creation of a research facility for the development of the SP machine

Cited by in corpus (8)

• The SP theory of intelligence and the representation and processing of knowledge in the brain
• Commonsense Reasoning, Commonsense Knowledge, and The SP Theory of Intelligence
• Software engineering and the SP Theory of Intelligence
• Solutions to problems with deep learning
• Interpreting Winograd Schemas Via the SP Theory of Intelligence and Its Realisation in the SP Computer Model
• Introduction to the SP theory of intelligence
• Problems in AI research and how the SP System may help to solve them
• Dual approach for object tracking based on optical flow and swarm intelligence