Mermin–Wagner fluctuations in 2D amorphous solids B Illing, S Fritschi, H Kaiser, CL Klix, G Maret, P Keim Proceedings of the National Academy of Sciences 114 (8), 1856-1861, 2017 | 161 | 2017 |
Biologically plausible deep learning—but how far can we go with shallow networks? B Illing, W Gerstner, J Brea Neural Networks 118, 90-101, 2019 | 115 | 2019 |
Local plasticity rules can learn deep representations using self-supervised contrastive predictions B Illing, J Ventura, G Bellec, W Gerstner Thirty-Fifth Conference on Neural Information Processing Systems, 2021, 2021 | 67 | 2021 |
Weight-space symmetry in deep networks gives rise to permutation saddles, connected by equal-loss valleys across the loss landscape J Brea, B Simsek, B Illing, W Gerstner arXiv preprint arXiv:1907.02911, 2019 | 49 | 2019 |
Strain pattern in supercooled liquids B Illing, S Fritschi, D Hajnal, C Klix, P Keim, M Fuchs Physical review letters 117 (20), 208002, 2016 | 40 | 2016 |
NMDA-driven dendritic modulation enables multitask representation learning in hierarchical sensory processing pathways WAM Wybo, MC Tsai, VAK Tran, B Illing, J Jordan, A Morrison, W Senn Proceedings of the National Academy of Sciences 120 (32), e2300558120, 2023 | 7 | 2023 |
Dendritic modulation enables multitask representation learning in hierarchical sensory processing pathways WAM Wybo, MC Tsai, VA Khoa Tran, B Illing, J Jordan, A Morrison, ... bioRxiv, 2022.11. 25.517941, 2022 | 2 | 2022 |
Dendritic modulation for multitask representation learning in deep feedforward networks W Wybo, A Morrison, J Jordan, W Senn, B Illing, M Tsai, VAK Tran Cosyne 2023, 2023 | | 2023 |
Biologically plausible unsupervised learning in shallow and deep neural networks BA Illing EPFL, 2021 | | 2021 |