Sequence memory is an essential attribute of natural and artificial
inte...
In recent years, significant attention in deep learning theory has been
...
We study how training molds the Riemannian geometry induced by neural ne...
Understanding how feature learning affects generalization is among the
f...
In this short note, we reify the connection between work on the storage
...
Inference in deep Bayesian neural networks is only fully understood in t...
Recent works have suggested that finite Bayesian neural networks may
out...
Bayesian neural networks are theoretically well-understood only in the
i...
The expressive power of artificial neural networks crucially depends on ...