Deep learning (DL), a subset of machine learning approaches, has emerged as a versatile
tool to assimilate large amounts of heterogeneous data and provide reliable predictions of …

Estimating the structure of directed acyclic graphs (DAGs, also known as Bayesian
networks) is a challenging problem since the search space of DAGs is combinatorial and …

Deep learning achieves state-of-the-art results in many tasks in computer vision and natural
language processing. However, recent works have shown that deep networks can be …

Federated learning (FL) is a promising technique for resolving the rising privacy and security
concerns. Its main ingredient is to cooperatively learn the model among the distributed …

We give a rigorous analysis of the statistical behavior of gradients in a randomly initialized
fully connected network N with ReLU activations. Our results show that the empirical …

In the context of the current sharing economy, the application of shared energy storage
(SES) among local integrated energy systems (LIESs) is underexplored. There is an urgent …

Training directed neural networks typically requires forward-propagating data through a
computation graph, followed by backpropagating error signal, to produce weight updates. All …

Deep-learning techniques appear to be poised to play very important roles in our processing
flows for inversion and interpretation of seismic data. The most successful seismic …

Transfer learning is important for foundation models to adapt to downstream tasks. However,
many foundation models are proprietary, so users must share their data with model owners …

Implicit deep learning prediction rules generalize the recursive rules of feedforward neural
networks. Such rules are based on the solution of a fixed-point equation involving a single …