Evolving Deep Networks Using HPC

@inproceedings{Young2017EvolvingDN,
  title={Evolving Deep Networks Using HPC},
  author={Steven R. Young and Derek C. Rose and J. Travis Johnston and William T. Heller and Thomas P. Karnowski and Thomas E. Potok and Robert M. Patton and Gabriel N. Perdue and Jonathan Miller},
  booktitle={MLHPC'17},
  year={2017}
}
While a large number of deep learning networks have been studied and published that produce outstanding results on natural image datasets, these datasets only make up a fraction of those to which deep learning can be applied. These datasets include text data, audio data, and arrays of sensors that have very different characteristics than natural images. As these "best" networks for natural images have been largely discovered through experimentation and cannot be proven optimal on some… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 14 CITATIONS

Evolving Energy Efficient Convolutional Neural Networks

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND

Exascale Deep Learning to Accelerate Cancer Research

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS

Scalable reinforcement-learning-based neural architecture search for cancer deep learning research

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Memetic evolution of deep neural networks

VIEW 5 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

A Modular Benchmarking Infrastructure for High-Performance and Reproducible Deep Learning

VIEW 2 EXCERPTS
CITES BACKGROUND

Epigenetic evolution of deep convolutional models

VIEW 2 EXCERPTS
CITES BACKGROUND & METHODS

Fine-Grained Exploitation of Mixed Precision for Faster CNN Training

VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS

On the automated, evolutionary design of neural networks: past, present, and future

VIEW 1 EXCERPT
CITES BACKGROUND

167-PFlops Deep Learning for Electron Microscopy: From Learning Physics to Atomic Manipulation

VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND