Now showing items 16-18 of 100

    • Spike-Based Winner-Take-All Computation: Fundamental Limits and Order-Optimal Circuits 

      Su, Lili; Chang, Chia-Jung; Lynch, Nancy (MIT Press - Journals, 2019)
      © 2019 Massachusetts Institute of Technology. Winner-take-all (WTA) refers to the neural operation that selects a (typ-ically small) group of neurons from a large neuron pool. It is conjectured to underlie many of the ...
    • Collaboratively Learning the Best Option on Graphs, Using Bounded Local Memory 

      Su, Lili; Zubeldia, Martin; Lynch, Nancy (Association for Computing Machinery (ACM), 2019)
      <jats:p>We consider multi-armed bandit problems in social groups wherein each individual has bounded memory and shares the common goal of learning the best arm/option. We say an individual learns the best option if eventually ...
    • Task-structured probabilistic I/O automata 

      Canetti, Ran; Cheung, Ling; Kaynar, Dilsun; Liskov, Moses; Lynch, Nancy; e.a. (Elsevier BV, 2018)
      © 2017 Elsevier Inc. Modeling frameworks such as Probabilistic I/O Automata (PIOA) and Markov Decision Processes permit both probabilistic and nondeterministic choices. In order to use these frameworks to express claims ...