Industrial recommender systems deal with extremely large action spaces--many millions of
items to recommend. Moreover, they need to serve billions of users, who are unique at any …

Recurrent neurons (and in particular LSTM cells) demonstrated to be efficient when used as
basic blocks to build sequence to sequence architectures, which represent the state-of-the …

Recurrent neural networks are widely used on time series data, yet such models often
ignore the underlying physical structures in such sequences. A new class of physics-based …

In this paper, we introduce a new 3D hand gesture recognition approach based on a deep
learning model. We propose a new Convolutional Neural Network (CNN) where sequences …

The selection of initial parameter values for gradient-based optimization of deep neural
networks is one of the most impactful hyperparameter choices in deep learning systems …

Circuits of biological neurons, such as in the functional parts of the brain can be modeled as
networks of coupled oscillators. Inspired by the ability of these systems to express a rich set …

Stability is a fundamental property of dynamical systems, yet to this date it has had little
bearing on the practice of recurrent neural networks. In this work, we conduct a thorough …

The exploding and vanishing gradient problem has been the major conceptual principle
behind most architecture and training improvements in recurrent neural networks (RNNs) …

A gated recurrent unit (GRU) is a successful recurrent neural network architecture for time-
series data. The GRU is typically trained using a gradient-based method, which is subject to …

Reinforcement Learning (RL) has been sought after to bring next-generation recommender
systems to further improve user experience on recommendation platforms. While the …