A mathematical theory of semantic development in deep neural networks
From MaRDI portal
Publication:5222757
DOI10.1073/pnas.1820226116zbMath1416.92018arXiv1810.10531OpenAlexW2898365215WikidataQ92124643 ScholiaQ92124643MaRDI QIDQ5222757
Andrew M. Saxe, James L. McClelland, Surya Ganguli
Publication date: 3 July 2019
Published in: Proceedings of the National Academy of Sciences (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1810.10531
Related Items
Exploring the common principal subspace of deep features in neural networks, Black holes and the loss landscape in machine learning, Artificial selection of communities drives the emergence of structured interactions, A new initialization method based on normed statistical spaces in deep networks, Unnamed Item