Robots have great potential to facilitate future therapies for children on the autism spectrum. However, existing robots lack the ability to automatically perceive and respond to human affect, which is necessary for establishing and maintaining engaging interactions. Moreover, their inference challenge is made harder by the fact that many individuals with autism have atypical and unusually dive...

Machine learning models, especially based on deep learning are used in everyday applications ranging from self driving cars to medical diagnostics. However, it is easy to trick such models using adversarial samples, indistinguishable from real samples to human eye, such samples can lead to incorrect classifications. Impact of adversarial samples is far-reaching and efficient detection of advers...

The medical field stands to see significant benefits from the recent advances in deep learning. Knowing the uncertainty in the decision made by any machine learning algorithm is of utmost importance for medical practitioners. This study demonstrates the utility of using Bayesian LSTMs for classification of medical time series. Four medical time series datasets are used to show the accuracy impr...

The efficiency of deep machine learning for automatic delineation of tumor areas has been demonstrated for intraoperative neuronavigation using active IRmapping with the use of the cold test. The proposed approach employs a matrix IR-imager to remotely register the space-time distribution of surface temperature pattern, which is determined by the dynamics of local cerebral blood flow. The advan...

Most contemporary multi-task learning methods assume linear models. This setting is considered shallow in the era of deep learning. In this paper, we present a new deep multi-task representation learning framework that learns cross-task sharing structure at every layer in a deep network. Our approach is based on generalising the matrix factorisation techniques explicitly or implicitly used by m...

This issue highlights the technical theme on “Deep Learning Applications,” one of most active areas in this new age AI and machine learning. Eight articles demonstrate progress made deep representation learning, neural network architectures, their multidomain applications. Three column debate decentralized AI, autonomous racing, big AI.

Bayesian modelling and variational inference are rooted in Bayesian statistics, and easily benefit from the vast literature in the field. In contrast, deep learning lacks a solid mathematical grounding. Instead, empirical developments in deep learning are often justified by metaphors, evading the unexplained principles at play. It is perhaps astonishing then that most modern deep learning model...