SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Politics : Evolution

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
Recommended by:
Solon
To: Greg or e who wrote (59487)10/6/2014 7:41:38 PM
From: TigerPaw1 Recommendation  Read Replies (2) of 69300
 
biological behavioral models

The artificial neural networks are modeled on biological examples.

When talking about them within the industry a lot of the same biological or medical terminology is used. Just as a crane can be said to "pick something up" just as an arm might pick something up, so are the words and terms of thinking applied to these circuits.

A good example that you might be able to actually see are the self driving automobiles that are being tested in California. These aren't just trains without engineers, or large versions of roomba vaccums which bounce around the roads. They are scary smart, but I know that each little perception is the output of a simple trained 3 layer network (or for flexibility it is a software simulation of a three layer parallel adder).

What most current neural network systems lack is a training feedback system which operates as it functions. This type of feature is being added so that the system can learn roads or better driving techniques as it drives, and that is not a huge leap from a network that incorporates a sense of it's own internal state in it's calculations and that is close to a network that is aware of itself.
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext