News for hackers. Stuff that matters.
Re:Study reveals how, when a synapse strengthens, its neighb... by tunnuz on Sunday June 24, 2018 @02:06PM (#17387567)
I wonder if the progress in artificial neural network technology is going to be correlated to discoveries on real neural networks.
Re:Study reveals how, when a synapse strengthens, its neighb... by amelius on Sunday June 24, 2018 @02:08PM (#17387578)
I'm still wondering about the natural equivalent of back-propagation.
Re:Study reveals how, when a synapse strengthens, its neighb... by no_identd on Sunday June 24, 2018 @03:15PM (#17387922)
Re:Study reveals how, when a synapse strengthens, its neighb... by p1esk on Sunday June 24, 2018 @04:25PM (#17388226)
I think the term "backpropagation" has a different meaning in neurobiology.
Re:Study reveals how, when a synapse strengthens, its neighb... by zerostar07 on Sunday June 24, 2018 @10:29PM (#17389549)
those are backpropagating spikes, not errors
Re:Study reveals how, when a synapse strengthens, its neighb... by SubiculumCode on Sunday June 24, 2018 @09:13PM (#17389302)
Isn't that mostly a supervised learning technique? Maybe the larger question is whether learning in the brain is better described as unsupervised or supervised.
Re:Study reveals how, when a synapse strengthens, its neighb... by mrep on Monday June 25, 2018 @02:18AM (#17390270)
I don't know how babies learn to initially use words but after that entails 99% supervised learning through school IMO nowadays. I would even argue that most new economic growth is the also the result of general supervised learning (aka, learning from others because the wealth of human knowledge is way more than anyone can learn in a million lifetimes and so the economic growth comes from continuously combining new ideas that combine other new ideas).
Re:Study reveals how, when a synapse strengthens, its neighb... by im3w1l on Monday June 25, 2018 @03:21AM (#17390525)
But we aren't beating kids when they get facts wrong and we aren't giving them candy when they are right. So studying how the reward signal is computed should be interesting.
Re:Study reveals how, when a synapse strengthens, its neighb... by mrep on Monday June 25, 2018 @11:01AM (#17392913)
Beating kids and giving them candy is way on the extreme side of reinforcement. Having good grades be praised by teachers/parents and bad grades be associated with disappointment is already pretty good since humans are highly receptive to other people's emotions.
Re:Study reveals how, when a synapse strengthens, its neighb... by SubiculumCode on Tuesday June 26, 2018 @04:28PM (#17403735)
Really we are being too static in the thinking about it. Supervised learning can essentially be done by one brain region supervising another that is being trained. It doesn't have to be outside the skull.
Re:Study reveals how, when a synapse strengthens, its neighb... by im3w1l on Tuesday June 26, 2018 @01:23AM (#17398055)
Yeah I agree! I'm just saying there's gotta be a lot of intricate machinery to make such subtle reinforcements work.