CBMM Memo Series: Recent submissions
Now showing items 1-3 of 145
-
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 ... -
On the Power of Decision Trees in Auto-Regressive Language Modeling
(Center for Brains, Minds and Machines (CBMM), 2024-09-27)Originally proposed for handling time series data, Auto-regressive Decision Trees (ARDTs) have not yet been explored for language modeling. This paper delves into both the theoretical and practical applications of ARDTs ...