Representational Drift as a Result of Implicit Regularization
Aviv Ratzon, Dorgham Khatib, Mariell Sellevoll, Genela Morris, Dori Derdikman, Omri Barak · COSYNE 2023
Sun, Mar 12, 2023
Recent studies show that, even in constant environments, the tuning of single neurons to outside world variables gradually changes over time in a variety of brain regions [1, 2, 3, 4, 5]. This phenomenon, termed representational drift, has changed the way we think about the stability of memory and perception, but its driving forces and properties are still mostly unknown. We combine data analysis and modeling to show that implicit regularization can partially explain drift. We train an artificial neural network on a predictive coding task. We continue training in the presence of noise after go