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.
I'm clear. That didn't prevent the authors from using that term anyway. And in their title, just to make sure not to confuse anyone.
EDIT : the author(s) of the press release used the word "upload". That term is nowhere to be found in the original paper as far as I can tell.
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.
It's a more accurate neuron model of some pretty weird neurons. In nearly all organisms, the vast majority of neurons fire all-or-nothing action potentials ("spikes"). C. elegans neurons do not.
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?
There’s a lot of work in artificial gene regulatory networks that suggest that the network topology not the implementation details is responsible for function. I think we learn more with a simplified model and then figure out why we are falling short of our expectations.
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…
From the summary, they’re not altering the topology of the network at all, just the connection strength between neurons.
While this isn’t the way a natural neural network would learn (I’m not sure a nematode can learn), it’s still interesting that you can take a copy of a natural neural network and force it to learn in this way.
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…
From the summary, they’re not altering the topology of the network at all, just the connection strength between neurons. While this isn’t the way a natural neural network would learn (I’m not sure a nematode can learn), it’s still interesting that you can take a copy of a natural neural network and force it to learn in this way.
I would expect there is an enormous set of random topologies that could be trained to balance a pole. Indeed, part of the elegant 'magic' of neural nets is that the topology is fairly irrelevant... the number of layers, the number of nodes, the manner in which they are connected... pretty much any configuration can get you into a mid 90% accuracy on MNIST (and emulating a basic PID algorithm is simpler than MNIST). Of course, I'm referring to basic tasks; clearly topologies matter a great deal with more sophisticated things.
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.
From what I understand, the complication is that each neurone acts behaves like a complex neural network by itself, so to get the same overall behavior, you would need many more fundamental units.
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...
This is very close to a P controller (like PID, but without the integral and derivative terms).