addressalign-toparrow-leftarrow-rightbackbellblockcalendarcameraccwcheckchevron-downchevron-leftchevron-rightchevron-small-downchevron-small-leftchevron-small-rightchevron-small-upchevron-upcircle-with-checkcircle-with-crosscircle-with-pluscrossdots-three-verticaleditemptyheartexporteye-with-lineeyefacebookfolderfullheartglobegmailgooglegroupshelp-with-circleimageimagesinstagramlinklocation-pinm-swarmSearchmailmessagesminusmoremuplabelShape 3 + Rectangle 1ShapeoutlookpersonJoin Group on CardStartprice-ribbonShapeShapeShapeShapeImported LayersImported LayersImported Layersshieldstartickettrashtriangle-downtriangle-uptwitteruserwarningyahoo

Spiking neural networks in artificial creatures

  • February 14 · 6:00 PM
  • Yahoo Trondheim

Mostly all neural networks in machine learning today are stateless, always giving the same output 'y' for an input 'x'.  Biological neurons on the other hand show more dynamic integration of input, with their output being similar to a binary on/off switch throughout time.

In this presentation you will learn about the similarities and distinctions between biological and artificial neurons, evolutionary algorithms, and fitness functions. You will also see a live simulation of these methods combined, where creatures evolve to find food in a randomized environment only using a simple spiking neural network to control them. As we will see, the end result of the creature's behavior is strikingly similar to that of small biological animals.

Presenter: Asgeir Berland from Inmeta 


There will be beer.

Welcome!


Join or login to comment.

  • Harald M.

    Yes, that was a great presentation by Asgeir! And many nice people! Very interesting indeed. I mentioned briefly that a topic for the next meeting could possibly be on how different science- and technology cultures vary in how they view Big Data. My own view - from a chemometrics/ qualimetrics / dynametrics / Big Data Cybernetics position is fleshed out in more detail in my 2015 paper: BIG DATA: where chemometrics can contribute
    (http://onlinelibrary.wiley.com/doi/10.1002/cem.2740/full ).

    Cheers, Harald Martens

    http://scholar.google.no/citations?user=60HNWsYAAAAJ&hl=no

    February 16

  • Asgeir B.

    Thanks for the positive feedback! I'm sad that I couldn't stay for longer. Below is a link of a working program if you want to toy around yourself in the testbed.

    https://github.com/Inmeta/OsloMaskinlaering/tree/master/2016.12.14%20SpikingNeuralNetworks

    1 · February 16

  • Eirik M.

    Very interesting talk!

    3 · February 15

  • Anton E.

    Very interesting topic and excellent presentation! Thank you Asgeir!

    2 · February 15

  • Stephen L.

    Interesting topic and a good review of Asgeir's Masters research.

    2 · February 15

  • Øystein N.

    Future contribution: I could report on the progress of the BIGMED lighthouse project on precision medicine at Oslo Univ. Hospital in a while...

    3 · February 7

  • Dan M.

    I could potentially do a talk about my work on global supply chains & environmental impacts. There was a lot of interest in a recent paper on biodiversity footprints (http://news.nationalgeographic.com/2017/01/maps-reveal-how-global-consumption-hurts-wildlife/ ). The larger project is about connecting observations of environmental impact to supply chains, with the idea that not just producers, but also intermediates and consumes should/can help reduce env. pressure. The code behind all this is not super sophisticated by computer scientist's standards but is reasonably interesting - we consider 5bn international supply chains linking 15000 sectors across 187 countries / 20 years / 18000 species.

    2 · January 17

  • Jørgen L.

    I'm not really sure that it's a good fit, but I'll put forward the name Leendert Wienhofen, researcher at Sintef IKT who works at a project using case-based reasoning in surgery planning at St. Olavs. Maybe this project or something else where they are using data science in health care would be interesting.

    3 · January 17

People in this
Meetup are also in:

Sign up

Meetup members, Log in

By clicking "Sign up" or "Sign up using Facebook", you confirm that you accept our Terms of Service & Privacy Policy