Deep learning often faces the challenge of efficiently processing dynami...
Quantum many-body problems are some of the most challenging problems in
...
We establish a direct connection between general tensor networks and dee...
We introduce a simple and efficient method, called Auxiliary Tuning, for...
Self-attention architectures, which are rapidly pushing the frontier in
...
We review the cost of training large-scale language models, and the driv...
Self-supervision techniques have allowed neural language models to advan...
Artificial Neural Networks were recently shown to be an efficient
repres...
The harnessing of modern computational abilities for many-body wave-func...
The key attribute that drives the unprecedented success of modern Recurr...
We present a novel tractable generative model that extends Sum-Product
N...
The driving force behind convolutional networks - the most successful de...
Expressive efficiency refers to the relation between two architectures A...
Casting neural networks in generative frameworks is a highly sought-afte...
It has long been conjectured that hypotheses spaces suitable for data th...
We present a deep layered architecture that generalizes convolutional ne...