Shallow neural networks process the features directly, while deep networks extract features
automatically along with the training. Both models suffer from overfitting or poor …

Normalization techniques are essential for accelerating the training and improving the
generalization of deep neural networks (DNNs), and have successfully been used in various …

Effectively predicting molecular interactions has the potential to accelerate molecular
dynamics by multiple orders of magnitude and thus revolutionize chemical simulations …

The emerging paradigm of federated learning (FL) strives to enable collaborative training of
deep models on the network edge without centrally aggregating raw data and hence …

This open-source book represents our attempt to make deep learning approachable,
teaching readers the concepts, the context, and the code. The entire book is drafted in …

Deep neural networks have been successfully used in diverse emerging domains to solve
real world complex problems with may more deep learning (DL) architectures, being …

Object detection, one of the most fundamental and challenging problems in computer vision,
seeks to locate object instances from a large number of predefined categories in natural …

In this paper, we investigate the problem of overfitting in deep reinforcement learning.
Among the most common benchmarks in RL, it is customary to use the same environments …

Abstract Invariant Risk Minimization (IRM) is an emerging invariant feature extracting
technique to help generalization with distributional shift. However, we find that there exists a …

Abstract Normalization layers (eg, Batch Normalization, Layer Normalization) were
introduced to help with optimization difficulties in very deep nets, but they clearly also help …