Generalization in data-driven models of primary visual cortex

no code implementations • ICLR 2021 • Konstantin-Klemens Lurz, Mohammad Bashiri, Konstantin Willeke, Akshay Jagadish, Eric Wang, Edgar Y. Walker, Santiago A Cadena, Taliah Muhammad, Erick Cobos, Andreas S. Tolias, Alexander S Ecker, Fabian H. Sinz

With this new readout we train our network on neural responses from mouse primary visual cortex (V1) and obtain a gain in performance of 7% compared to the previous state-of-the-art network.

Transfer Learning

CNNs efficiently learn long-range dependencies

no code implementations • NeurIPS Workshop SVRHM 2020 • Timo Lüddecke, Alexander S Ecker

The role of feedback (or recurrent) connections is a fundamental question in neuroscience and machine learning.