user avatar
John Hopfield
@HopfieldJohn
I work on neural networks and biology, often from the view point of my roots in physics. Professor @PrincetonNeuro.
Joined July 2020
15
Following
5,913
Followers
Posts
  • Pinned
    user avatar
    John Hopfield
    @HopfieldJohn
    Aug 18, 2020
    Dense Associative Memories, aka modern Hopfield networks, have a huge memory storage capacity. But are they biologically realistic? In our new paper with @DimaKrotov we argue that they can be written in terms of biological variables. arxiv.org/abs/2008.06996
  • user avatar
    John Hopfield
    @HopfieldJohn
    Oct 28, 2024
    This award is very hard to respond to. I have received many hundred congratulatory notes, from former students, post-docs, Princeton University juniors and seniors, funding agencies and foundations, authors, signature collectors, amateurs, elementary school neural network
    147K
  • user avatar
    John Hopfield
    @HopfieldJohn
    Oct 31, 2024
    A few days ago, I spoke with @Nature about my work at the interface between disciplines nature.com/articles/d4158…
    60K
  • user avatar
    John Hopfield
    @HopfieldJohn
    Jul 21, 2021
    Everybody knows about Lyapunov functions in simple networks with local non-linearities. What this paper shows is that with symmetric feedback a Lyapunov function can be constructed for arbitrary non-linear activation functions involving groups of neurons.
    user avatar
    Dmitry Krotov
    @DimaKrotov
    Jul 15, 2021
    One of the great features of deep learning is that we can easily stack multiple layers (e.g. dense, conv, attention) with arbitrary activation functions to build a useful feedforward network. Wouldn’t it be cool if we could do the same for Modern Hopfield Networks with feedback?
  • user avatar
    John Hopfield
    @HopfieldJohn
    Jul 7, 2020
    New @icmlconf paper on biologically inspired unsupervised similarity search with @wrong_whp @DimaKrotov @LeopoldGrinberg arxiv.org/abs/2001.04907 #icml2020
  • user avatar
    John Hopfield
    @HopfieldJohn
    Dec 8, 2020
    Very much looking forward to hearing this dialog Wednesday
  • user avatar
    John Hopfield
    @HopfieldJohn
    Nov 21, 2022
    Francis 'Frank' Schmitt already had an amazing view in 1962 of where neuroscience needed to go if you were serious about understanding higher brain function. His Neuroscience Research Program had a set of Associates spread across the relevant fields.
    user avatar
    Nicole C Rust, PhD
    @NicoleCRust
    Nov 8, 2022
    Replying to @TonyZador and @suzanahh
    Yes! And some exciting things emerged out of the multidisciplinary meetings Schmidt organized on this topic - like @HopfieldJohn ’s inspiration to create Hopfield networks.
  • user avatar
    John Hopfield
    @HopfieldJohn
    Nov 21, 2022
    Replying to @HopfieldJohn
    I was welcome in this group because I knew so little about conventional neuroscience that my questions threatened no one.
  • user avatar
    John Hopfield
    @HopfieldJohn
    Jul 21, 2021
    Replying to @HopfieldJohn
    The mathematical idea that makes this possible is the Lagrangian for the dynamical system. This system can be turned into a multi-layer network with simultaneous forward and feedback flow of information.
  • user avatar
    John Hopfield
    @HopfieldJohn
    Apr 29, 2021
    Please check out Dima's presentation at #ICLR2021 next Tuesday.
    user avatar
    Dmitry Krotov
    @DimaKrotov
    Apr 29, 2021
    What is Dense Associative Memory or Modern Hopfield Network❓ Our paper will be presented at #ICLR2021 next week. I want to highlight some of the main results here. Paper: arxiv.org/abs/2008.06996 Longer seminar: youtube.com/watch?v=_QVUyX… Thread 🧵1/N
    00:00
  • user avatar
    John Hopfield
    @HopfieldJohn
    Nov 21, 2022
    Replying to @HopfieldJohn
    Their scientific interaction at small meetings of the Associates was intended to usefully drive the science. Alas, this meeting was more of the prima-donna behavior of a set of scientific leaders, rather than a coherent chorus, which frustrated Frank Schmitt.
  • user avatar
    John Hopfield
    @HopfieldJohn
    Nov 8, 2020
    A perceptive commentary on the Biden election and the US political divide from the English experience of Thatcherism and Brexit. On with the celebration jarwillis.com/2020/11/07/on-… via @JARWillis
    On with the celebration
    From jarwillis.com
  • user avatar
    John Hopfield
    @HopfieldJohn
    Oct 26, 2020
    A feeling of community is so important!
    user avatar
    APS Division of Biological Physics
    @ApsDbio
    Oct 24, 2020
    Hello world! Welcome to the brand new twitter home of APS-DBIO! Connecting members (including potential future members) of APS-DBIO. Please help us grow, follow + retweet! @MARGARETSCHEUNG @squishycell1 @DrJennyRoss @ApsDsoft @wbialek @oritpeleg @phybiofunc @cplcillinois
  • user avatar
    John Hopfield
    @HopfieldJohn
    Apr 29, 2021
    Replying to @DimaKrotov
    For maximal information storage, the power n (in notations of Krotov&Hopfield 2016) or equivalently the inverse temperature of the softmax activation function (in notations of Ramsauer et al. 2020) should be large.