Can neural networks benefit from objectives that encourage iterative convergent computations? A case study of ResNets and object classification

• Samuel Lippl ,

  Roles Conceptualization, Formal analysis, Investigation, Methodology, Visualization, Writing – original draft, Writing – review & editing

  * E-mail: samuel.lippl@columbia.edu

  Affiliations Zuckerman Mind Brain Behavior Institute, Columbia University, New York, NY, United States of America, Department of Neuroscience, Columbia University, New York, NY, United States of America, Center for Theoretical Neuroscience, Columbia University, New York, NY, United States of America

  https://orcid.org/0000-0002-8169-087X

  ⨯
• Benjamin Peters,

  Roles Conceptualization, Investigation, Methodology, Supervision, Validation, Writing – original draft, Writing – review & editing

  Affiliations Zuckerman Mind Brain Behavior Institute, Columbia University, New York, NY, United States of America, School of Psychology and Neuroscience, University of Glasgow, Glasgow, United Kingdom

  https://orcid.org/0000-0002-0948-8976

  ⨯
• Nikolaus Kriegeskorte

  Roles Conceptualization, Funding acquisition, Resources, Supervision, Visualization, Writing – review & editing

  Affiliations Zuckerman Mind Brain Behavior Institute, Columbia University, New York, NY, United States of America, Department of Neuroscience, Columbia University, New York, NY, United States of America, Department of Psychology, Columbia University, New York, NY, United States of America, Affiliated member, Electrical Engineering, Columbia University, New York, NY, United States of America

  ⨯