Dear Visitor,

Our system has found that you are using an ad-blocking browser add-on.

We just wanted to let you know that our site content is, of course, available to you absolutely free of charge.

Our ads are the only way we have to be able to bring you the latest high-quality content, which is written by professional journalists, with the help of editors, graphic designers, and our site production and I.T. staff, as well as many other talented people who work around the clock for this site.

So, we ask you to add this site to your Ad Blocker’s "white list" or to simply disable your Ad Blocker while visiting this site.

Continue on this site freely
You are here: Home / EST Contributed Content / Intro to the SP Theory of Intelligence
AI Innovation: Introducing The SP Theory of Intelligence
AI Innovation: Introducing The SP Theory of Intelligence
News as reported by the company Like this on Facebook Tweet this Link thison Linkedin Link this on Google Plus
The SP Theory of Intelligence: Simplification and Integration Across AI and Related Areas -- By J Gerard Wolff, Director of

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, 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.

Additional Resources

- More information about the SP programme of research
- A PDF with more detail
- Contact details

Image credit: iStock/Artist's Concept.

Tell Us What You Think


M. Stuart:
Posted: 2018-03-21 @ 1:16pm PT
If Gerry Wolff's previous preoccupation with failed concentrating solar technology and its application in the energy sector is any indication of intellectual ROI, then I would suspect his current preoccupation with SP fills a much-needed void in the artificial intelligence field.

Like Us on FacebookFollow Us on Twitter
© Copyright 2018 NewsFactor Network. All rights reserved. Member of Accuserve Ad Network.