Slashdot Mirror
Researchers Create Simulation Of a Simple Worm's Neural Network (tuwien.ac.at)
ClockEndGooner writes: Researchers at the Technische Universitat Wein have created a simulation of a simple worm's neural network, and have been able to replicate its natural behavior to completely mimic the worm's natural reflexive behavior. According to the article, using a simple neural network of 300 neurons, the simulation of "the worm can find its way, eat bacteria and react to certain external stimuli. It can, for example, react to a touch on its body. A reflexive response is triggered and the worm squirms away. This behavior is determined by the worm's nerve cells and the strength of the connections between them. When this simple reflex network is recreated on a computer, the simulated worm reacts in exactly the same way to a virtual stimulation -- not because anybody programmed it to do so, but because this kind of behavior is hard-wired in its neural network." Using the same neural network without adding any additional nerve cells, Mathias Lechner, Radu Grosu, and Ramin Hasani were able to have the nematode simulation learn to balance a pole "just by tuning the strength of the synaptic connections. This basic idea (tuning the connections between nerve cells) is also the characteristic feature of any natural learning process."
I, for one, welcome our simple worm AI overlords.
I even RTFA and can't tell. This seems a remarkable accomplishment.
they took the neural net (without the weights & biases) of a worm, but modified/trained all its parameters. it's not really related to a worm at this point. I guess all this shows is that you don't need a lot of neurons to build useful systems.
At first glace, while distracted, the title looked like it said "Researchers Create Simulation Of a Simple Woman's Neural Network".
... it was the lovely folks at the Technische Universität Wien. Though I am quite sure they would welcome a glass of Wein (wine) every once in a while too.
So we're well on our way to simulating better congresscritters?
They should get together with the Grandroids guy, I imagine he'd have a lot to share, and vice versa.
On Soylent News. Along with <strike> , <spoiler> , <sub> , <sup> , <abbr> , and some other really useful things that actually work. Also much more careful editing of TFS's, 10 mod points per day for everyone without forcing you to be anonymous if you want to comment, zero ads, and various useful amenities like handling characters beyond ASCII. The code's open, and you can contribute, too.
It works just like Slashdot, except, you know, it actually works.
I've fallen off your lawn, and I can't get up.
It just so happens that C. elegans is one of the few multicellular organisms for which all cell fates during development are mostly deterministic and completely known.
The actual worm itself has exactly 302 neurons, and their connections have been mapped.
http://www.wormatlas.org/herma...
Wein?!? like wine? Are you drunk?
Can we say for definite that this worm isn't a conscious being based on this research?
FTA:
"But no human being has written even one line of code for this controller"
Umm, excuse me? Its a simulation running on a computer, of course someone wrote some code - probably quite a lot of it in fact for both the training and the actual running even if these researchers themselves just used some off the shelf library such as tensorflow.
ANNs are simply code running processing data whatever the high level logical view of them may be. The fact that the data (weights and thresholds) itself is the main driver of end behaviour rather than hard coded program logic doesn't mean its not a computer program.
Anyway, neurons are simply complex highly interlinked analogue logic gates - given enough time it would be possible to codify any neural network in boolean logic using thousands or millions of if-then statements and jumps.
C. Elegans has been neurally simulation mapped for quite some time, and some engineers have already tied the neurons to actual physical sensors and motors to create a robot. I would really like to know how this simulation differs from the prior full neuron simulations.
Computer Neural networks work nothing like the human brain. Even calling these programs "neural networks" is misleading. Saying you have created a "simple worms neural network" is a complete lie. It implies that they have replicated worm level brains in the computer. They havent'.
But is it small enough to use for fishing?
That's very cool!
They have only about 400 neurons.
Touch them and they will reflexively shout, "Racist!" and then try to tax you.
and elect the result.
"Researchers Create Simulation Of a Simple Woman's Neural Network." And I was thinking... Holy shit, why?
302 neurons should be enough for everybody.
This is not AI. We don't have AI and we never will.
Even if you full simulate every neuron in a human brain, it won't be AI. Just engineering.
How many neurons to simulate a Slashdot editor? The article did not claim that the simulation of the worm could "find its way, eat bacteria and react to certain external stimuli". Only the actual worms do that.
It's not a neural network. It's a simulation of a neural circuit.
It's not the whole worm's nervous system, it is just one small component of the nervous system: "We model the tap-withdrawal (TW) neural circuit..."
This is a small paper about modeling nerves. It has nothing to do with neural nets, nothing to do with AI, and nothing even to do with computers, any more than modelling global warming or engineering roof snow loads has to do with computers, other than the fact that the computations are done with a computer.
Hasn't this already been done? What about the OpenWorm Project?
This is it. Fuck Musk and AI and Bitcoin. This is real future news.
They did this with roundworms already, and put it on a Lego robot.
than your average Trump supporter!
Lobsters are the next step.