News for hackers. Stuff that matters.
Re:The Unreasonable Effectiveness of Recurrent Neural Networks by alextgordon on Thursday May 21, 2015 @10:13PM (#9586337)
Also, brain chemistry. You can't give psychoactive drugs to a circuit board...
Re:The Unreasonable Effectiveness of Recurrent Neural Networks by zaroth on Thursday May 21, 2015 @11:17PM (#9586446)
I'll bet in a matter of time we will find that indeed you can give something quite analogous to "psychoactive drugs" to a strong AI!
Re:The Unreasonable Effectiveness of Recurrent Neural Networks by Lambdanaut on Friday May 22, 2015 @10:19AM (#9588413)
I've done some thinking on this.

If you can computationally define how different common neurotransmitters affect the function of neurons at a broad, high level, then you can create your "psychoactive drug" by just writing a routine that excessively applies the function that those neurotransmitters represent.

An artificial serotonin reuptake inhibitor would just allow the serotonin-like activity to more active in the model.

Re:The Unreasonable Effectiveness of Recurrent Neural Networks by antocv on Friday May 22, 2015 @04:34AM (#9587127)
Turbo button suddenly has a real meaning.
Re:The Unreasonable Effectiveness of Recurrent Neural Networks by tim333 on Friday May 22, 2015 @03:50PM (#9590576)
The parameter Karpathy call 'temperature' seems not dissimilar in effect to a psychoactive drug, low temperature corresponding roughly to sober and high to being a bit, well, high.