Ai Forums Home Welcome Guest    Tuesday, September 26, 2017
Ai Site > Ai Forums > The Artificial Intelligence Forum > Limits to pattern-matching Last PostsLoginRegisterWhy Register
Topic: Limits to pattern-matching

useruser
posted 9/1/2016  22:21Reply with quote
It appears from what I have seen looking at the white papers on this site suggest something along the ideas of evolution in which the training is designed to rapidly create a form of natural selection from ever increasing pattern matching. On a book I read on Turing, he suggested the hope for outcome was that once a machine learned to do one thing it might more easily find the pattern more rapidly to solve a new problem. This unfortunately does not appear to be the case with a hal regardless of how evolved the personality which raises a question to the whole concept of natural selection to arriving at A.I. by pattern matching alone. Any comments?


keghn
posted 9/2/2016  00:39Send e-mail to userReply with quote
Matching patterns and in sequence.

You can collect a lot of data and then look for repeating patterns. Which
is the way does not do. Or you can create a small algorithm and have
look at data that it is attuned too. This is what the brain does.


AiHasBeenSolved
posted 9/17/2016  20:15Send e-mail to userReply with quote
Yesterday I was doing pattern matching in the MindForth AGI and then last night I had a dream about coding AI.

 Dreams of Strong AI

AiHasBeenSolved
posted 10/3/2016  04:56Send e-mail to userReply with quote
Now I am offering Mentifex AI theory and software to entrepreneurs free of charge.

 Mentifex
  1  
'Send Send email to user    Reply with quote Reply with quote    Edit message Edit message

Forums Home    Hal and other child machines    Alan and other chatbots    Language Mind and Consciousness  
Contact Us Terms of Use