Time series modeling is a well-established problem, which often requires...
Visual data such as images and videos are typically modeled as
discretiz...
State space models (SSM) have recently been shown to be very effective a...
Developing architectures suitable for modeling raw audio is a challengin...
A central goal of sequence modeling is designing a single principled mod...
Recurrent neural networks (RNNs), temporal convolutions, and neural
diff...
The industrial machine learning pipeline requires iterating on model
fea...
Machine learning models are often deployed in different settings than th...
Novel neural architectures, training strategies, and the availability of...
Despite impressive performance on standard benchmarks, deep neural netwo...
Classifiers in machine learning are often brittle when deployed. Particu...
In many cases an intelligent agent may want to learn how to mimic a sing...
Optimal stopping problems consider the question of deciding when to stop...
We present Octopus, an AI agent to jointly balance three conflicting tas...