Re: [agi] Re: Real AGI Brain

[immortal . discoveries]

On Friday, January 31, 2020, at 8:29 PM, Matt Mahoney wrote:
> All of this complexity is in keeping with Legg's proof that powerful 
> predictors are necessarily complex. You end up writing lots of code to handle 
> special cases and obscure file types to squeeze out just a little more 
> compression. You can see why it can take 10 years or more to develop a good 
> compressor.
For hand-crafted rules. But our goal is to make AI that learns its own rules. 
For example a compressor may be told by the programmer T=t or move this section 
to end of file or turn off these models at x time or see double space as single 
space but the algorithm can learn these on its own.
------------------------------------------
Artificial General Intelligence List: AGI
Permalink: 
https://agi.topicbox.com/groups/agi/T409fc28ec41e6e3a-M2b8d5408cd0964ffda42690b
Delivery options: https://agi.topicbox.com/groups/agi/subscription