In recent years significant breakthroughs in exploring big data, recognition of complex
patterns, and predicting intricate variables have been made. One efficient way of analyzing …

Graphs are widely used as a popular representation of the network structure of connected
data. Graph data can be found in a broad spectrum of application domains such as social …

Anomaly detection is an important problem that has been well-studied within diverse
research areas and application domains. The aim of this survey is two-fold, firstly we present …

Deep autoencoders, and other deep neural networks, have demonstrated their effectiveness
in discovering non-linear features across many problem domains. However, in many real …

Many of the existing machine learning algorithms, both supervised and unsupervised,
depend on the quality of the input characteristics to generate a good model. The amount of …

A video prediction model that generalizes to diverse scenes would enable intelligent agents
such as robots to perform a variety of tasks via planning with the model. However, while …

Given a scale expansion of Internet of Things for sustainable resource management in smart
cities, proper design of an intrusion detection system (IDS) is critical to safeguard the future …

We present a review on the recent advances and emerging opportunities around the theme
of analyzing deep neural networks (DNNs) with information-theoretic methods. We first …

Can we automatically learn meaningful semantic feature representations when training
labels are absent? Several recent unsupervised deep learning approaches have attempted …

The presence of outliers can severely degrade learned representations and performance of
deep learning methods and hence disproportionately affect the training process, leading to …