Search Results for author:
Found 2 papers, 0 papers with code
MLPs Learn In-Context
We further show that MLPs outperform Transformers on a subset of ICL tasks designed to test relational reasoning.
Contrasting random and learned features in deep Bayesian linear regression
Moreover, we show that the leading-order correction to the kernel-limit learning curve cannot distinguish between random feature models and deep networks in which all layers are trained.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
