Slashdot Mirror

← Back to Stories (view on slashdot.org)

Researchers Create Simulation Of a Simple Worm's Neural Network (tuwien.ac.at)

Posted by BeauHD on from the new-tricks dept.

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."

15 of 75 comments (clear)

  1. Simple Worm Overlords by Anonymous Coward · · Score: 3, Funny

    I, for one, welcome our simple worm AI overlords.

  2. Is the code open sourced? by aviators99 · · Score: 2

    I even RTFA and can't tell. This seems a remarkable accomplishment.

    1. Re:Is the code open sourced? by tonique · · Score: 2
      Neither can I. The article links to the article at Google Docs and that one links to a Youtube video. Wait, it says they used RoboSchool RoboschoolInvertedPendulum-v1 environment, whatever that is. The quotation for that one is

      [11] J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov. Proximal policy optimization algorithms. CoRR, abs/1707.06347, 2017.

  3. #NotAllWorms by Anonymous Coward · · Score: 5, Informative

    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.

    1. Re:#NotAllWorms by Plus1Entropy · · Score: 2

      First paragraph yo.

      C. elegans is the only living being whose neural system has been analysed completely. It can be drawn as a circuit diagram or reproduced by computer software, so that the neural activity of the worm is simulated by a computer program.

      They took the simulation of the worm's brain and trained it to balance a stick. They didn't build a neural network from the ground up with the sole intent of balancing a stick.

      --
      Only crack the nuts that crack. You don't put the ones that don't crack in the sack.
    2. Re:#NotAllWorms by Anne+Thwacks · · Score: 3, Interesting
      In nature, neural nets are dynamically rewired.

      Think of the net starting with all potential connections. the neurones sum their inputs in a weighted manner.

      Over time, some connections get stronger, and others weaker. Eventually some die out completely.

      Some of you may see this as entirely and completely analagous to how the logic and routing are programmed in FPGAs.

      At night, the whole shebang goes off-line for a bug fix session (Some of you may see this as entirely and completely analagous to how FPGAs are put in programming mode for the logic and routing to be programmed).

      Some of you may think that either:

      • A lot of these "neural net" research projects are a scam, or
      • A lot of these "neural net" research projects are a serious waste of time, or
      • The people involved in these projects might be better off reading up on FPGAs before they set out to prove the blindingly obvious, rather badly.

      Yes, I have been saying this since Xilinx released their first chip.

      Yes, it would appear that an FPGA is more intelligent than 90% of politicians. Appearances can be deceptive. Its probably more like 99%

      --
      Sent from my ASR33 using ASCII
    3. Re:#NotAllWorms by Cyberax · · Score: 5, Informative

      Yes, but for this particular worm it isn't. C.Elegans has fixed wiring that has been mapped completely.

    4. Re:#NotAllWorms by Freischutz · · Score: 2

      First paragraph yo.

      C. elegans is the only living being whose neural system has been analysed completely. It can be drawn as a circuit diagram or reproduced by computer software, so that the neural activity of the worm is simulated by a computer program.

      They took the simulation of the worm's brain and trained it to balance a stick. They didn't build a neural network from the ground up with the sole intent of balancing a stick.

      Yup, in fact the FA says:

      This behaviour can be perfectly explained: it 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, then 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 behaviour is hard-wired in its neural network.

      While narrow-AI that can totally trash any human at chess or something but sucks at everything else is interesting for limited applications it is neural networks that is the future of AI. It will be a long time before it is possible to design a set of algorithms that can outperform the result of 4,2 billion years of evolution. If you can simulate the neural network/brain of an insect or something of that level of sophistication, complete with its ocular and audio sensors you have the basics for the AI to run a self driving car better than anything we have today. We currently solve the problem of a self driving car with computers that are huge and use a monstrous amount of energy compared to what nature came up with. Nature packed the solution to a similar problem into a portion of the brain of an ant that lives on the amount of energy contained in the minuscule amount of protein it consumes daily. So, if you are an AI researcher, and if you find yourself proudly looking at the server running your self driving car software, take a look at an ant and realise that you have a looooooong way to go.

    5. Re:#NotAllWorms by religionofpeas · · Score: 3, Insightful

      I can't wait to see your trained ant drive a car.

  4. I hate to be THAT one but ... by Anonymous Coward · · Score: 4, Informative

    ... 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.

    1. Re:I hate to be THAT one but ... by Mister+Liberty · · Score: 3, Funny

      They were probably thinking "Wein, Worms and Gesang."

    2. Re:I hate to be THAT one but ... by anon+mouse-cow-aard · · Score: 3, Informative

      clarification: in German, Wein is wine, Wien is Vienna... I suppose there could be Viennese wine, would would be wiener wein, but that sounds gross in English.

  5. C. elegans neuron map by Guppy · · Score: 4, Informative

    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...

  6. More iles by 110010001000 · · Score: 2

    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'.

  7. Re:Conscious being by religionofpeas · · Score: 2

    First you have to define exactly what you mean by "conscious being", and then we can answer the question.