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.
Second, the 3D topology of a neuron is IMO more complex than reducing it to an FP32 activation threshold (all IMO of course).
Finally, I have to admit as a former biologist, I'm intrigued by microtubule activity and it seems like Dileep George and even Geoffrey Hinton are heading towards smarter but fewer neurons as opposed to just increasing the neuron count. Not surprisingly, the deep learning digerati are resisting this notion mightily just like the SVM peeps harped on neural networks until they kicked them in the keester.
TLDR: It's still early, and I'm biased that there are some interesting twists and turns yet to unfold here.