Live data from Hacker News

Learning through ferroelectric domain dynamics in solid-state synapses

nature.com

11–14 of 14 posts

Re: Learning through ferroelectric domain dynamics in solid-state synapses

#11
post #6

Correct me if I'm dead wrong here, but isn't "software machine learning" taking advantage from all the neurons being "interconnected", similar to a brain? How does that work with physical (discrete?) components as in this case?

There's good reason to believe that different parts of the brain are quasi-specialized to particular applications. In a sense, this applies to particular software artificial neural networks (ANN) as well, particularly if the various hyper-parameters are fixed (number of neural units per layer, etc). One of the primary advantages of software ANNs over hardware ANNs (which don't really exist yet) would be the ability t…

It's far from clear that STDP is sufficient to the brain's learning mechanisms, though it is certainly necessary at some scales and stages.

The possibility space between relatively simple and insufficiently general unsupervise/clustering approaches and rigid SGD schemes is large, and probably contains the brain's true inference engine. Personally, I am excited by some of the ideas brought forward in this Bengio paper: https://arxiv.org/pdf/1602.05179.pdf

Re: Learning through ferroelectric domain dynamics in solid-state synapses

#12
post #8

It appears that we might have jumped on the transistor metaphor too quick and to intensely. I believe not everything is binary in the brain, even if the resulting executive action is. Patterns, for example, might not be.

Most computational biology researchers would be more likely to compare synapses to memristors nowadays.

Re: Learning through ferroelectric domain dynamics in solid-state synapses

#13
post #8

It appears that we might have jumped on the transistor metaphor too quick and to intensely. I believe not everything is binary in the brain, even if the resulting executive action is. Patterns, for example, might not be.

While neural action potentials are binary (either absent or identical to every other AP) they encode temporally an analog signal (internal charge, ion concentration) with amplitude in proportion to frequency.

Re: Learning through ferroelectric domain dynamics in solid-state synapses

#14
post #8

It appears that we might have jumped on the transistor metaphor too quick and to intensely. I believe not everything is binary in the brain, even if the resulting executive action is. Patterns, for example, might not be.

Who are "we"?

For example, "Almost everybody accepts that the brain does a tremendous amount of analog processing. The controversy lies in whether there is anything digital about it." [1]

[1]: http://www.rle.mit.edu/acbs/pdfpublications/journal_papers/a... (page 30 of the PDF, labelled 1630)

Post reply on HN