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

Nematode Neural System Uploaded to a Computer and Trained to Balance a Pole

tuwien.ac.at

Post reply on HN
Print view View original

21–30 of 38 posts

Re: Nematode Neural System Uploaded to a Computer and Trained to Balance a Pole

#21

Post by red75prime »

grondilu wrote: post #12

I vaguely recall that experts consider artificial neural networks to be a very gross approximation of biological ones. They often state that one reason we don't have AI today is that we don't really know how the brain and the neurons it is made of work. Then I wonder : how does openworm deal with that lack of knowledge? Is there any chance progress in modeling C. Elegans could be used to improve machine learning?

It could be other way around. Evolution invented imprecise and roundabout way of doing gradient descent.

Re: Nematode Neural System Uploaded to a Computer and Trained to Balance a Pole

#22

Post by dsego »

egeozcan wrote: post #8
gargarplex wrote: post #6

Wait until we can 3D print a C. Elegans. A new kind of matrix printer.

Maybe The Great Filter (in the context of the Fermi paradox) is this: People printing their own organisms? (only half-joking)

We're in a simulation.

Re: Nematode Neural System Uploaded to a Computer and Trained to Balance a Pole

#23

Post by gwern »

anewhnaccount2 wrote: post #5
Y_Y wrote: post #3

Neural network balances pole while programmers mumble something vague about C. Elegans. Non-story.

This uses a more accurate neuron model than your everyday neural networks.

Nevertheless, Cartpole is a trivial RL task which only requires a few neurons to solve, much less hundreds. Since they're training it in silico, I'm not sure what this demonstrates other than you can cudgel a vaguely spiking-like neural network into learning a simple task. It's not a C. elegans behavior.

Re: Nematode Neural System Uploaded to a Computer and Trained to Balance a Pole

#24

Post by gambler »

I first learned about C. elegans neuron-mapping project from this Society of Mind video:

https://www.youtube.com/watch?v=6Px0livk6m8

My immediate interest was in seeing the differences and similarities between real and simulated worm. I haven't spent much time searching for resulting papers, but it's been 7 years since then and I'm not aware of any ground-breaking publications on the subject.

Unless I'm missing something massive, describing this paper as training the worm to "balance a pole at the tip of its tail" is highly misleading.

In this paper researchers use an external algorithm to tweak parameters of a part of worm's neural model until that part can perform a certain task. The neural circuit effectively serves as a controller for a mechanism that has nothing to do with the original worm. The task, the setup, the subset of the model and the training algorithms are all chosen by the researchers.

Re: Nematode Neural System Uploaded to a Computer and Trained to Balance a Pole

#25

Post by guskel »

gwern wrote: post #23
anewhnaccount2 wrote: post #5

Earlier quoted context omitted.

This uses a more accurate neuron model than your everyday neural networks.

Nevertheless, Cartpole is a trivial RL task which only requires a few neurons to solve, much less hundreds. Since they're training it in silico, I'm not sure what this demonstrates other than you can cudgel a vaguely spiking-like neural network into learning a simple task. It's not a C. elegans behavior.

Cartpole solved with 1 neuron, no weights.

https://gym.openai.com/evaluations/eval_A7rFUDisQiOsADyvqYhV...

Re: Nematode Neural System Uploaded to a Computer and Trained to Balance a Pole

#26

Post by gwern »

guskel wrote: post #25
gwern wrote: post #23

Earlier quoted context omitted.

Nevertheless, Cartpole is a trivial RL task which only requires a few neurons to solve, much less hundreds. Since they're training it in silico, I'm not sure what this demonstrates other than you can cudgel a vaguely spiking-like neural network into learning a simple task. It's not a C. elegans behavior.

Cartpole solved with 1 neuron, no weights. https://gym.openai.com/evaluations/eval_A7rFUDisQiOsADyvqYhV...

I rest my case. :)

Re: Nematode Neural System Uploaded to a Computer and Trained to Balance a Pole

#27

Post by nonbel »

gambler wrote: post #24

I first learned about C. elegans neuron-mapping project from this Society of Mind video: https://www.youtube.com/watch?v=6Px0livk6m8 My immediate interest was in seeing the differences and similarities between real and simulated worm. I haven't spent much time searching for resulting papers, but it's been 7 years since then and I'm not aware of any ground-breaking publications on the subject. Unless I'm missing somet…

I think their idea is to use biologically inspired network architectures. Looking at Fig1 of the paper[1], it seems they have drawn the schematic in an overly complicated way...

For example, FWD and REV motor neurons are totally determined by AVB and AVA sensory neurons so can be left out. I would bet if it is worked out this reduces to some simple ANN architecture.

[1] https://docs.google.com/viewer?a=v&pid=sites&srcid=ZGVmYXVsd...

Re: Nematode Neural System Uploaded to a Computer and Trained to Balance a Pole

#28

Post by gambler »

molyss wrote: post #7

It’ll become interesting when we can teach the worm before “uploading”it, and the resulting NN already knows how to balance that pole without any further training. As is, The article sounds underwhelming

The worm isn't "uploaded". Scientists painstakingly mapped out the physical structure of its neurons using some genetic engineering and lasers. This structure does not change from worm to worm.

Re: Nematode Neural System Uploaded to a Computer and Trained to Balance a Pole

#29

Post by gambler »

nonbel wrote: post #27
gambler wrote: post #24

I first learned about C. elegans neuron-mapping project from this Society of Mind video: https://www.youtube.com/watch?v=6Px0livk6m8 My immediate interest was in seeing the differences and similarities between real and simulated worm. I haven't spent much time searching for resulting papers, but it's been 7 years since then and I'm not aware of any ground-breaking publications on the subject. Unless I'm missing somet…

I think their idea is to use biologically inspired network architectures. Looking at Fig1 of the paper[1], it seems they have drawn the schematic in an overly complicated way... For example, FWD and REV motor neurons are totally determined by AVB and AVA sensory neurons so can be left out. I would bet if it is worked out this reduces to some simple ANN architecture. [1] https://docs.google.com/viewer?a=v&pid=sites&sr…

>I think their idea is to use biologically inspired network architectures.

It seems that way. This approach could have interesting applications in engineering. But I wish it wasn't pitched to imply that "machine learning and the activity of our brain the same on a fundamental level". (This is a direct quote from the article, except it was posed as a rhetorical question there.)

Re: Nematode Neural System Uploaded to a Computer and Trained to Balance a Pole

#30

Post by tzahola »

grondilu wrote: post #12

I vaguely recall that experts consider artificial neural networks to be a very gross approximation of biological ones. They often state that one reason we don't have AI today is that we don't really know how the brain and the neurons it is made of work. Then I wonder : how does openworm deal with that lack of knowledge? Is there any chance progress in modeling C. Elegans could be used to improve machine learning?

We believe that the underlying implementation (biological neuron vs logistic function) doesn’t matter as long as it has the fundamental properties from which intelligence can emerge. Like how you can build computers from gears, relays, vacuum tubes or silicon - as long as you have a transistor-like nonlinearity to work with, you’re good.
Post reply on HN