The global volume of digital data is expected to reach 175 zettabytes by 2025. The volume,
variety and velocity of water-related data are increasing due to large-scale sensor networks …

The rapid development in machine learning and in the emergence of new data sources
makes it possible to examine and predict traffic conditions in smart cities more accurately …

This textbook establishes a theoretical framework for understanding deep learning models
of practical relevance. With an approach that borrows from theoretical physics, Roberts and …

An introduction to a broad range of topics in deep learning, covering mathematical and
conceptual background, deep learning techniques used in industry, and research …

Neural network models have a reputation for being black boxes. We propose to monitor the
features at every layer of a model and measure how suitable they are for classification. We …

Abstract Recurrent Neural Networks with Long Short-Term Memory (LSTM) make use of
gating mechanisms to mitigate exploding and vanishing gradients when learning long-term …

Deep learning methods possess many processing layers to understand the stratified
representation of data and have achieved state-of-art results in several domains. Recently …

Recurrent Neural Networks are powerful tools for modeling sequences. They are flexibly
extensible and can incorporate various kinds of information including temporal order. These …

Inventors have long dreamed of creating machines that think. Ancient Greek myths tell of
intelligent objects, such as animated statues of human beings and tables that arrive full of …

We study the behavior of untrained neural networks whose weights and biases are
randomly distributed using mean field theory. We show the existence of depth scales that …