The SP Theory of Intelligence: Simplification and Integration Across AI and Related Areas -- By J Gerard Wolff, Director of CognitionResearch.org
The SP Theory of Intelligence
and its realisation in the SP Computer Model
is a system designed to simplify and integrate ideas across AI (artificial intelligence) and related fields. As the basis for a high-parallel SP machine, it has many potential benefits and applications.
In broad terms, the SP system is a brain-like system that takes in New information through its senses and stores some or all of it in compressed form as Old information.
Simplicity and Power = Information Compression
The name "SP" stands for Simplicity and Power, two ideas which, together, mean the same as information compression. This is because information compression may be seen to be a process of maximising 'simplicity' in a body of information, by reducing redundancy in that information, whilst at the same time retaining as much as possible of its non-redundant expressive 'power'.
SP-Multiple-Alignment Is Key
A central idea in the SP system is the powerful concept of SP-multiple-alignment, borrowed and adapted from the concept of 'multiple sequence alignment' in bioinformatics.
The SP-multiple-alignment concept is the basis of the SP system's versatility in aspects of intelligence, in the representation of diverse kinds of knowledge, and in the seamless integration of diverse aspects of intelligence and diverse kinds of knowledge, in any combination.
SP-multiple-alignment may prove to be as significant for 'intelligence' as is DNA for biological sciences: it may prove to be the 'double helix' of intelligence.
In a 'neural' version of the SP theory called SP-Neural, abstract constructs and processes in the system may be realised in terms of neurons and their interconnections. In this connection, it is relevant to mention that the SP system is quite different from deep learning in 'artificial neural networks' and has substantial advantages compared with such systems, including 'deep learning'.
The SP System Has Strengths and Potential in Several Areas
Versatility in aspects of intelligence including unsupervised learning, the analysis and production of natural language; pattern recognition that is robust in the face of errors in data; pattern recognition at multiple levels of abstraction;
computer vision; and several more.
Reasoning. Kinds of reasoning exhibited by the SP system include: one-step 'deductive' reasoning; chains of reasoning; abductive reasoning; reasoning with probabilistic networks and trees; reasoning with 'rules'; nonmonotonic reasoning and reasoning with default values; Bayesian reasoning with 'explaining away'; and several more.
Versatility in the representation of knowledge. The SP system may represent several different kinds of knowledge, including: the syntax of natural languages; class-inclusion hierarchies (with or without cross classification); part-whole
hierarchies; and several more.
Potential benefits and applications of the SP system include potential to help solve problems with: big data, autonomous robots, medical diagnosis, computer vision, neuroscience, cutting the amounts of data needed for learning, promoting transparency in the representation of knowledge, solving the deep learning problem of 'catastrophic forgetting', and several more.
About the Author
Dr Gerry Wolff is the director of CognitionResearch.org, a not-for-profit research body developing the SP system. Dr Wolff has extensive experience of university research and teaching, and many publications in peer-reviewed journals, collections of papers, and conference papers.
- More information about the SP programme of research
- A PDF with more detail
- Contact details