CBMM Memo Series
Recent Submissions
-
Self-Assembly of a Biologically Plausible Learning Circuit
(Center for Brains, Minds and Machines (CBMM), 2024-12-28)Over the last four decades, the amazing success of deep learning has been driven by the use of Stochastic Gradient Descent (SGD) as the main optimization technique. The default implementation for the computation of the ... -
On Generalization Bounds for Neural Networks with Low Rank Layers
(Center for Brains, Minds and Machines (CBMM), 2024-10-11)While previous optimization results have suggested that deep neural networks tend to favour low-rank weight matrices, the implications of this inductive bias on generalization bounds remain under-explored. In this paper, ... -
Formation of Representations in Neural Networks
(Center for Brains, Minds and Machines (CBMM), 2024-10-07)Understanding neural representations will help open the black box of neural networks and advance our scientific understanding of modern AI systems. However, how complex, structured, and transferable representations emerge ...
RSS 1.0