home.social

#hopfield — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #hopfield, aggregated by home.social.

  1. Der #Nobelpreis für Physik geht in diesem Jahr an John J. #Hopfield und Geoffrey E. #Hinton für ihre wegweisenden Entdeckungen und Entwicklungen, die #MaschinellesLernen mit künstlichen neuronalen Netzen ermöglichen.
    Warum diese Entscheidung unsere Kollegin #EstherTobschall (Fachreferentin für #Physik) doch ziemlich durcheinandergebracht hat, erklärt sie hier im #TIBBlog: blog.tib.eu/2024/12/09/physik-

  2. Remember last week's #nobel2024 #nobelprize in physics ?
    I fondly remember my student days and the course on #NeuralNets in summer 1994 given by Helge Ritter
    from #unibielefeld, where I learned about the #Hopfield model for the first time.
    I was able to dig out my 30 year old lecture notes, including the citation of the seminal 1984 PNAS paper, see below. Neural Networks have come a long was since then ! Yours, Steffen

  3. Scommetto che nel premio #Nobel per la #fisica a #Hopfield e #Hinton c'è (anche) lo zampino di Giorgio #Parisi. Negli anni '80 c'era una certa eccitazione tra i fisici (almeno per quello che ho potuto vedere a Roma) intorno alle reti neuronali, e penso che da lì gli sia venuta l'idea di occuparsi dei vetri di spin.

  4. Congrats to #Hopfield and #Hinton for their #Nobel prize.

    I guess that #Rosenblatt would have also deserved to be on the team for his initial implementation of the perceptron, considering that a Hopfield network (the building idea of today’s neural networks) was largely an extension of that idea, but unfortunately he’s gone for a while.

    The idea of neural networks is indeed worth of a Nobel prize.

    Whether it should be in #physics, I’m not that sure though.

    https://www.nobelprize.org/prizes/physics/2024/press-release/

  5. Brody and #Hopfield (2003) showed how networks of #SpikingNeurons (#SNN) can be used to process temporal information based on computations on the timing of spikes rather than the rate of spikes. This is particularly relevant in the context of #OlfactoryProcessing, where the timing of spikes in the olfactory bulb is crucial for encoding odor information. Here is a quick tutorial, that recapitulates the main concepts of that network using #NEST #simulator:

    🌍 fabriziomusacchio.com/blog/202

    #CompNeuro