Artificial Intelligence

    

A Proposed Solution to Problems in Learning the Knowledge Needed by Self-Driving Vehicles

Authors: J Gerard Wolff

Three problems in learning knowledge for self-driving vehicles are: how a finite sample of information about driving, N, can yield an ability to deal with the infinity of possible driving situations; the problem of generalising from N without over- or under-generalisation; and how to weed out errors in N. A theory developed with computer models to explain a child’s learning of his or her first language, now incorporated in the SP System, suggests: compress N as much as possible by a process that creates a grammar, G, and an encoding of N in terms of G called E. Then discard E which contains all or most of the errors in N, and retain G which solves the first two problems.

Comments: 15 Pages.

Download: PDF

Submission history

[v1] 2021-09-13 10:29:37

Unique-IP document downloads: 251 times

Vixra.org is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. Vixra.org will not be responsible for any consequences of actions that result from any form of use of any documents on this website.

Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.

comments powered by Disqus