15 citations · 81 across the 21 of their papers we have counts for
21 papers
Discriminative Enhancement for Single Channel Audio Source Separation using Deep Neural Networks
Emad M. Grais, Gerard Roma, Andrew J. R. Simpson +1
The sources separated by most single channel audio source separation techniques are usually distorted and each separated source contains residual signals from the other sources. To…
Hierarchical Conflict Propagation: Sequence Learning in a Recurrent Deep Neural Network
Andrew J. R. Simpson
Recurrent neural networks (RNN) are capable of learning to encode and exploit activation history over an arbitrary timescale. However, in practice, state of the art gradient descen…
Qualitative Projection Using Deep Neural Networks
Andrew J. R. Simpson
Deep neural networks (DNN) abstract by demodulating the output of linear filters. In this article, we refine this definition of abstraction to show that the inputs of a DNN are abs…
Uniform Learning in a Deep Neural Network via "Oddball" Stochastic Gradient Descent
Andrew J. R. Simpson
When training deep neural networks, it is typically assumed that the training examples are uniformly difficult to learn. Or, to restate, it is assumed that the training error will…
On-the-Fly Learning in a Perpetual Learning Machine
Andrew J. R. Simpson
Despite the promise of brain-inspired machine learning, deep neural networks (DNN) have frustratingly failed to bridge the deceptively large gap between learning and memory. Here,…
"Oddball SGD": Novelty Driven Stochastic Gradient Descent for Training Deep Neural Networks
Andrew J. R. Simpson
Stochastic Gradient Descent (SGD) is arguably the most popular of the machine learning methods applied to training deep neural networks (DNN) today. It has recently been demonstrat…