BEGIN:VCALENDAR VERSION:2.0 PRODID:researchseminars.org CALSCALE:GREGORIAN X-WR-CALNAME:researchseminars.org BEGIN:VEVENT SUMMARY:Dmitry Krotov (Watson AI Lab and IBM Research in Cambridge) DTSTART:20220414T160000Z DTEND:20220414T170000Z DTSTAMP:20260423T003242Z UID:MPML/70 DESCRIPTION:Title: Mo dern Hopfield Networks in AI and Neurobiology\nby Dmitry Krotov (Watso n AI Lab and IBM Research in Cambridge) as part of Mathematics\, Physics a nd Machine Learning (IST\, Lisbon)\n\n\nAbstract\n

Modern Hopfield Netwo rks or Dense Associative Memories are recurrent neural networks with fixed point attractor states that are described by an energy function. In contr ast to conventional Hopfield Networks\, their modern versions have a very large memory storage capacity\, which makes them appealing tools for many problems in machine learning and cognitive and neuro-sciences. In this tal k I will introduce an intuition and a mathematical formulation of this cla ss of models\, and will give examples of problems in AI that can be tackle d using these new ideas. I will also explain how different individual mode ls of this class (e.g. hierarchical memories\, attention mechanism in tran sformers\, etc.) arise from their general mathematical formulation with th e Lagrangian functions.

\n\n

References:

\n\n
    \n
  1. D.Krotov\, J.Hopfield\, "Dense associative memory for pattern recognition"
    2. \n
  2. D.Krotov\, J.Hopfield\, "Large Associat ive Memory Problem in Neurobiology and Machine Learning"
    3. \n
  3. M.Demircigil\, et al.\, "On a mod el of associative memory with huge storage capacity"
    4. \n
  4. H.Ramsauer\, et al.\, "Hopfield Netwo rks is All You Need"
    5. \n
  5. D.Krotov\, "Hierarchical Associative Memory"
    6. \n
\n\n

&n bsp\;

\n LOCATION:https://researchseminars.org/talk/MPML/70/ END:VEVENT END:VCALENDAR