As research attention in deep learning has been focusing on pushing empirical results to a higher peak, remarkable progress made the performance race of machine applications past years. Yet based artificial neural networks still remains difficult understand as it is considered black-box approach. A lack understanding from theoretical perspective would not only hinder employment them where high-...

The important aspect of this layer-wise training procedure is that, provided the number of features per layer does not decrease, [6] showed that each extra layer increases a variational lower bound on the log probability of data. So layer-by-layer training can be repeated several times1 to learn a deep, hierarchical model in which each layer of features captures strong high-order correlations b...

We propose the B c → B * u γ decay as the most suitable probe for the flavour changing neutral transition c → uγ. We estimate the short and long distance contributions to this decay within the standard model and we find them to be comparable; this is in contrast to radia-tive decays of D mesons, that are completely dominated by the long distance contributions. Since the c → uγ transition is ver...

Predictive maintenance (PdM) is an advanced technique to predict the time failure (TTF) of a system. PdM collects sensor data on health system, processes information using analytics, and then establishes data-driven models that can forecast system failure. Deep neural networks are increasingly being used as these owing their high predictive accuracy efficiency. However, deep often criticized “b...

The variety and complexity of accents pose a huge challenge to robust Automatic Speech Recognition (ASR). Some previous work has attempted address such problems, however most the current approaches either require prior knowledge about target accent, or cannot handle unseen accent-unspecific standard speech. In this work, we aim improve multi-accent speech recognition in end-to-end&#x00A0...