Synaptic balancing: A biologically plausible local learning rule that provably increases neural network noise robustness without sacrificing task performance

• Christopher H. Stock,

  Roles Conceptualization, Data curation, Formal analysis, Investigation, Methodology, Project administration, Software, Validation, Visualization, Writing – original draft, Writing – review & editing

  Affiliation Neuroscience Graduate Program, Stanford University School of Medicine, Stanford, California, United States of America

  https://orcid.org/0000-0002-4579-660X

  ⨯
• Sarah E. Harvey ,

  Roles Formal analysis, Investigation, Methodology, Project administration, Visualization, Writing – review & editing

  * E-mail: harveys@stanford.edu

  Affiliation Department of Applied Physics, Stanford University, Stanford, California, United States of America

  https://orcid.org/0000-0003-2601-7487

  ⨯
• Samuel A. Ocko,

  Roles Conceptualization, Investigation, Methodology, Supervision, Writing – review & editing

  Affiliation Department of Applied Physics, Stanford University, Stanford, California, United States of America

  https://orcid.org/0000-0003-3426-4517

  ⨯
• Surya Ganguli

  Roles Funding acquisition, Resources, Writing – review & editing

  Affiliations Department of Applied Physics, Stanford University, Stanford, California, United States of America, Stanford Institute for Human-Centered Artificial Intelligence, Stanford University, Stanford, California, United States of America

  https://orcid.org/0000-0002-9264-7551

  ⨯