Recurrent Neural Networks are ubiquitous and pervasive in many artificial intelligence
applications such as speech recognition, predictive healthcare, creative art, and so on …

Classically, data interpolation with a parametrized model class is possible as long as the
number of parameters is larger than the number of equations to be satisfied. A puzzling …

Cellular sheaves equip graphs with a``geometrical''structure by assigning vector spaces and
linear maps to nodes and edges. Graph Neural Networks (GNNs) implicitly assume a graph …

What does a neural network encode about a concept as we traverse through the layers?
Interpretability in machine learning is undoubtedly important, but the calculations of neural …

Due to the fast inference and good performance, discriminative learning methods have been
widely studied in image denoising. However, these methods mostly learn a specific model …

This paper seeks to answer the question: as the (near-) orthogonality of weights is found to
be a favorable property for training deep convolutional neural networks, how can we enforce …

We propose heavy ball neural ordinary differential equations (HBNODEs), leveraging the
continuous limit of the classical momentum accelerated gradient descent, to improve neural …

This paper develops the FastRNN and FastGRNN algorithms to address the twin RNN
limitations of inaccurate training and inefficient prediction. Previous approaches have …

Word embeddings are well known to capture linguistic regularities of the language on which
they are trained. Researchers also observe that these regularities can transfer across …

We introduce a novel approach to perform first-order optimization with orthogonal and
unitary constraints. This approach is based on a parametrization stemming from Lie group …