• Dynamics of randomly connected neural networks and inference in the presence of hidden nodes 

      Battistin, Claudia (Doctoral theses at NTNU;2018:380, Doctoral thesis, 2018)
      Dynamikken til randomiserte nevrale nettverk og inferens med tilstedeværelse av skjulte noder Hjernen koder informasjon i populasjoner av nevroner, i motsetning til i enkeltceller. Modeller av nevrale nettverk kan hjelpe ...
    • Learning with unknowns: analyzing biological data in the presence of hidden variables 

      Battistin, Claudia; Dunn, Benjamin Adric; Roudi, Yasser (Journal article, 2017)
      Despite our improved ability to probe biological systems at a higher spatio-temporal resolution, the high dimensionality of the biological systems often prevents sufficient sampling of the state space. Even with large scale ...
    • The appropriateness of ignorance in the inverse kinetic Ising model 

      Dunn, Benjamin Adric; Battistin, Claudia (Journal article; Peer reviewed, 2017)
      We develop efficient ways to consider and correct for the effects of hidden units for the paradigmatic case of the inverse kinetic Ising model with fully asymmetric couplings. We identify two sources of error in reconstructing ...
    • The Stochastic Complexity of Spin Models: Are Pairwise Models Really Simple? 

      Beretta, Alberto; Battistin, Claudia; de Mulatier, Clelia; Mastromatteo, Iacopo; Marsili, Matteo (Journal article; Peer reviewed, 2018)
      Models can be simple for different reasons: because they yield a simple and computationally efficient interpretation of a generic dataset (e.g., in terms of pairwise dependencies)—as in statistical learning—or because they ...