Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A deep learning framework for neuroscience

nature.com

Post reply on HN
Print view View original

21–30 of 37 posts

Re: A deep learning framework for neuroscience

#21

Post by randcraw »

kristjankalm wrote: post #5
dr_dshiv wrote: post #2

Anyone up for a summary? I didn't get much from the abstract.

they're arguing that articifial neural nets are useful models of brain function and anatomy. a lot of people in the field of neuroscience strongly disagree, hence their attempt to outline the utility of ANNs.

No, I don't think so. In the abstract the authors propose that ANNs may be useful to model the brain in three ways: 1) objective functions (brain-mediated physiological outcomes), 2) learning rules (how patterns are recognized and knowledge is gained), and 3) 'architectures' (which I assume to mean patterns of neural wiring and how info flows).

They are NOT proposing that neural nets architectures are analogous to brain architectures. I'm guessing their focus is on the lowest level activities in simple brains, perhaps afferent/efferent sensory perception, metabolic and physiological regulatory control -- the kind of things instrumented in worms like C. Elegans.

Re: A deep learning framework for neuroscience

#22

Post by CodiePetersen »

coward12345678 wrote: post #11

My 8 month old daughter suffers from cortical visual impairment after contracting bacterial meningitis caused by e coli during the birthing process. She had to have a bilateral cranitomy to have isolated areas of the infection carved out of her brain tissue. Looking at this article, i wonder if we'll ever be able to figure any of this out. I feel pretty hopeless about the entire situation.

I don't think we need to have a full understanding of the brain to make progress on those fronts. If you look at neuralink (https://www.youtube.com/watch?v=r-vbh3t7WVI) there is some pretty amazing brain computer interfacing that is already happening. If we assume Moore's law hold up with neural sensor resolution, then within 10-15 years there will be as many input sensors as there are cones in the human eye. There are also plenty of other already existing technologies that can help aid in making her life easier.

I'm not saying "don't worry about it" as an uncle with two nieces I know how difficult it would be just to ignore something. You want your family and dependents to have happy full lives and every little struggle makes you worry and think. But what I am saying is, have a little hope. When you see articles like this, they are normally talking about theoretical and philosophical meanings of what intelligence and consciousness is, there is plenty of solid practical and applied science and progress that relates to your daughter's situation.

Don't get yourself worked up about the ponderings of math and computer nerds. The real life changing stuff is not being done in AI right now, its being done in universities, hospitals, and laboratories by scientists, doctors, and professors.

Re: A deep learning framework for neuroscience

#23

Post by ilyaeck »

coward12345678 wrote: post #11

My 8 month old daughter suffers from cortical visual impairment after contracting bacterial meningitis caused by e coli during the birthing process. She had to have a bilateral cranitomy to have isolated areas of the infection carved out of her brain tissue. Looking at this article, i wonder if we'll ever be able to figure any of this out. I feel pretty hopeless about the entire situation.

I feel your pain. But please, do not lose hope! The good news is there is now exponential progress is neuroscience and brain-machine interfaces. And above all, try focus on what your child does have or can have. Our weaknesses sometimes turn out to be strengths.

Re: A deep learning framework for neuroscience

#24

Post by neuronerd »

briga wrote: post #19
neuronerd wrote: post #16

Earlier quoted context omitted.

In a range of domains, in particular higher level brain areas, DL models trained on imagine are already the best predictive models of brain function. If they are better than all other models at describing the data, why would we say they have nothing to do with neuroscience?

As far as I know there is no evidence that the brain has any analogue to the back-propagation used to train pretty much all modern neural networks. Back-propagation is a good way to optimize neural networks, but it doesn't seem to be the way brains optimize neural networks.

well, the original paper has a pretty good summary of how the brain may actually do backdrop.

Re: A deep learning framework for neuroscience

#25

Post by skohan »

crawfordcomeaux wrote: post #14
skohan wrote: post #9

Earlier quoted context omitted.

> Advances in network architecture (e.g. the recent trend towards skip connections and parallel processes) is likely to give insight to how an underlying, more complex system is likely to operate. Maybe . The thing about these advances in ANNs is, so we have any reason to believe they have anything to do with the way biological neural networks work? It might be the case that these kinds of advances correlate to a mor…

From studying ANNs, I've reconceived of how I view myself from a programmatic perspective. I have used the resulting models to change myself in useful ways. If they're not perfectly accurate, they may still be accurate enough to be useful. The trick, to me, is to avoid falling into the trap of thinking imperfect models aren't useful. Then the accuracy matters less. An example of a useful intuition was realizing choos…

It's fine and good that ANNs can serve as a metaphor for your own mind. That's something very different than saying they're going to be useful in unraveling the scientific mysteries of the brain.

Re: A deep learning framework for neuroscience

#26

Post by univalent »

coward12345678 wrote: post #11

My 8 month old daughter suffers from cortical visual impairment after contracting bacterial meningitis caused by e coli during the birthing process. She had to have a bilateral cranitomy to have isolated areas of the infection carved out of her brain tissue. Looking at this article, i wonder if we'll ever be able to figure any of this out. I feel pretty hopeless about the entire situation.

I'm so sorry to hear that :( Hang in there.

Re: A deep learning framework for neuroscience

#27

Post by kristjankalm »

randcraw wrote: post #21
kristjankalm wrote: post #5

Earlier quoted context omitted.

they're arguing that articifial neural nets are useful models of brain function and anatomy. a lot of people in the field of neuroscience strongly disagree, hence their attempt to outline the utility of ANNs.

No, I don't think so. In the abstract the authors propose that ANNs may be useful to model the brain in three ways: 1) objective functions (brain-mediated physiological outcomes), 2) learning rules (how patterns are recognized and knowledge is gained), and 3) 'architectures' (which I assume to mean patterns of neural wiring and how info flows). They are NOT proposing that neural nets architectures are analogous to br…

> I'm guessing their focus is on the lowest level activities in simple brains, perhaps afferent/efferent sensory perception, metabolic and physiological regulatory control -- the kind of things instrumented in worms like C. Elegans.

could be but then most of the authors of the paper work in human cognition so I'm slightly skepical that their focus is going to be at the level of cellular biology

Re: A deep learning framework for neuroscience

#28

Post by endswapper »

I find it disappointing that the paper makes no mention of Numenta, TBToI or HTM. How is what they are proposing not already included in Numenta's work (informally, of course)? Plus, Numenta's work seems to go much further confronting biological plausibility head-on.

Re: A deep learning framework for neuroscience

#29

Post by randcraw »

kristjankalm wrote: post #27
randcraw wrote: post #21

Earlier quoted context omitted.

No, I don't think so. In the abstract the authors propose that ANNs may be useful to model the brain in three ways: 1) objective functions (brain-mediated physiological outcomes), 2) learning rules (how patterns are recognized and knowledge is gained), and 3) 'architectures' (which I assume to mean patterns of neural wiring and how info flows). They are NOT proposing that neural nets architectures are analogous to br…

> I'm guessing their focus is on the lowest level activities in simple brains, perhaps afferent/efferent sensory perception, metabolic and physiological regulatory control -- the kind of things instrumented in worms like C. Elegans. could be but then most of the authors of the paper work in human cognition so I'm slightly skepical that their focus is going to be at the level of cellular biology

Yeah, it's be nice if they offered an illustration of how they'd approach an amenable problem.

Re: A deep learning framework for neuroscience

#30

Post by joycian »

neuronerd wrote: post #24
briga wrote: post #19

Earlier quoted context omitted.

As far as I know there is no evidence that the brain has any analogue to the back-propagation used to train pretty much all modern neural networks. Back-propagation is a good way to optimize neural networks, but it doesn't seem to be the way brains optimize neural networks.

well, the original paper has a pretty good summary of how the brain may actually do backdrop.

What do you mean by "original paper" here?
Post reply on HN