Transparency and granularity in the SP Theory of Intelligence and its realisation in the SP Computer Model

09/07/2020
by   J Gerard Wolff, et al.
0

This chapter describes how the SP System, meaning the SP Theory of Intelligence, and its realisation as the SP Computer Model, may promote transparency and granularity in AI, and some other areas of application. The chapter describes how transparency in the workings and output of the SP Computer Model may be achieved via three routes: 1) the program provides a very full audit trail for such processes as recognition, reasoning, analysis of language, and so on. There is also an explicit audit trail for the unsupervised learning of new knowledge; 2) knowledge from the system is likely to be granular and easy for people to understand; and 3) there are seven principles for the organisation of knowledge which are central in the workings of the SP System and also very familiar to people (eg chunking-with-codes, part-whole hierarchies, and class-inclusion hierarchies), and that kind of familiarity in the way knowledge is structured by the system, is likely to be important in the interpretability, explainability, and transparency of that knowledge. Examples from the SP Computer Model are shown throughout the chapter.

READ FULL TEXT

page 5

page 12

research
10/09/2018

Interpreting Winograd Schemas Via the SP Theory of Intelligence and Its Realisation in the SP Computer Model

In 'Winograd Schema' (WS) sentences like "The city councilmen refused th...
research
09/02/2020

Problems in AI research and how the SP System may help to solve them

This paper describes problems in AI research and how the SP System may h...
research
11/18/2020

Redistricting Algorithms

Why not have a computer just draw a map? This is something you hear a lo...
research
09/29/2020

Signs for Ethical AI: A Route Towards Transparency

Artificial Intelligence (AI) has recently raised to the point where it h...
research
05/05/2022

Artificial Intelligence and Structural Injustice: Foundations for Equity, Values, and Responsibility

This chapter argues for a structural injustice approach to the governanc...
research
03/01/2023

21^st Century Statistical Disclosure Limitation: Motivations and Challenges

This chapter examines the motivations and imperatives for modernizing ho...
research
03/09/2023

Users are the North Star for AI Transparency

Despite widespread calls for transparent artificial intelligence systems...

Please sign up or login with your details

Forgot password? Click here to reset