Search Results for author:
Found 18 papers, 1 papers with code
Hierarchical Conflict Propagation: Sequence Learning in a Recurrent Deep Neural Network
Recurrent neural networks (RNN) are capable of learning to encode and exploit activation history over an arbitrary timescale.
Qualitative Projection Using Deep Neural Networks
Deep neural networks (DNN) abstract by demodulating the output of linear filters.
Uniform Learning in a Deep Neural Network via "Oddball" Stochastic Gradient Descent
When training deep neural networks, it is typically assumed that the training examples are uniformly difficult to learn.
"Oddball SGD": Novelty Driven Stochastic Gradient Descent for Training Deep Neural Networks
Stochastic Gradient Descent (SGD) is arguably the most popular of the machine learning methods applied to training deep neural networks (DNN) today.
Taming the ReLU with Parallel Dither in a Deep Neural Network
Rectified Linear Units (ReLU) seem to have displaced traditional 'smooth' nonlinearities as activation-function-du-jour in many - but not all - deep neural network (DNN) applications.
Use it or Lose it: Selective Memory and Forgetting in a Perpetual Learning Machine
In a recent article we described a new type of deep neural network - a Perpetual Learning Machine (PLM) - which is capable of learning 'on the fly' like a brain by existing in a state of Perpetual Stochastic Gradient Descent (PSGD).
On-the-Fly Learning in a Perpetual Learning Machine
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.
Parallel Dither and Dropout for Regularising Deep Neural Networks
Effective regularisation during training can mean the difference between success and failure for deep neural networks.
Dither is Better than Dropout for Regularising Deep Neural Networks
Regularisation of deep neural networks (DNN) during training is critical to performance.
Instant Learning: Parallel Deep Neural Networks and Convolutional Bootstrapping
Although deep neural networks (DNN) are able to scale with direct advances in computational power (e. g., memory and processing speed), they are not well suited to exploit the recent trends for parallel architectures.
Deep Karaoke: Extracting Vocals from Musical Mixtures Using a Convolutional Deep Neural Network
Identification and extraction of singing voice from within musical mixtures is a key challenge in source separation and machine audition.
Deep Transform: Cocktail Party Source Separation via Complex Convolution in a Deep Neural Network
Convolutional deep neural networks (DNN) are state of the art in many engineering problems but have not yet addressed the issue of how to deal with complex spectrograms.
Probabilistic Binary-Mask Cocktail-Party Source Separation in a Convolutional Deep Neural Network
Separation of competing speech is a key challenge in signal processing and a feat routinely performed by the human auditory brain.
Deep Transform: Cocktail Party Source Separation via Probabilistic Re-Synthesis
In cocktail party listening scenarios, the human brain is able to separate competing speech signals.
Deep Transform: Time-Domain Audio Error Correction via Probabilistic Re-Synthesis
In the process of recording, storage and transmission of time-domain audio signals, errors may be introduced that are difficult to correct in an unsupervised way.
Deep Transform: Error Correction via Probabilistic Re-Synthesis
Errors in data are usually unwelcome and so some means to correct them is useful.
Abstract Learning via Demodulation in a Deep Neural Network
Here, we demonstrate that DNN learn abstract representations by a process of demodulation.
Over-Sampling in a Deep Neural Network
Deep neural networks (DNN) are the state of the art on many engineering problems such as computer vision and audition.
