
-
On the Generalization Benefit of Noise in Stochastic Gradient Descent
It has long been argued that minibatch stochastic gradient descent can g...
read it
-
Sparse GPU Kernels for Deep Learning
Scientific workloads have traditionally exploited high levels of sparsit...
read it
-
AlgebraNets
Neural networks have historically been built layerwise from the set of f...
read it
-
A Practical Sparse Approximation for Real Time Recurrent Learning
Current methods for training recurrent neural networks are based on back...
read it
-
End-to-End Adversarial Text-to-Speech
Modern text-to-speech synthesis pipelines typically involve multiple pro...
read it
-
Rigging the Lottery: Making All Tickets Winners
Sparse neural networks have been shown to be more parameter and compute ...
read it
-
Fast Sparse ConvNets
Historically, the pursuit of efficient inference has been one of the dri...
read it
-
High Fidelity Speech Synthesis with Adversarial Networks
Generative adversarial networks have seen rapid development in recent ye...
read it
-
The Difficulty of Training Sparse Neural Networks
We investigate the difficulties of training sparse neural networks and m...
read it
-
Non-Differentiable Supervised Learning with Evolution Strategies and Hybrid Methods
In this work we show that Evolution Strategies (ES) are a viable method ...
read it
-
The State of Sparsity in Deep Neural Networks
We rigorously evaluate three state-of-the-art techniques for inducing sp...
read it
-
Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset
Generating musical audio directly with neural networks is notoriously di...
read it
-
Efficient Neural Audio Synthesis
Sequential models achieve state-of-the-art results in audio, visual and ...
read it
-
Parallel WaveNet: Fast High-Fidelity Speech Synthesis
The recently-developed WaveNet architecture is the current state of the ...
read it
-
Onsets and Frames: Dual-Objective Piano Transcription
We consider the problem of transcribing polyphonic piano music with an e...
read it
-
Mixed Precision Training
Deep neural networks have enabled progress in a wide variety of applicat...
read it
-
Exploring Sparsity in Recurrent Neural Networks
Recurrent Neural Networks (RNN) are widely used to solve a variety of pr...
read it
-
DSD: Dense-Sparse-Dense Training for Deep Neural Networks
Modern deep neural networks have a large number of parameters, making th...
read it
-
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
We show that an end-to-end deep learning approach can be used to recogni...
read it
-
Deep Speech: Scaling up end-to-end speech recognition
We present a state-of-the-art speech recognition system developed using ...
read it