Corpus ID: 3067546

FractalNet: Ultra-Deep Neural Networks without Residuals

@article{Larsson2017FractalNetUN,
  title={FractalNet: Ultra-Deep Neural Networks without Residuals},
  author={Gustav Larsson and M. Maire and Gregory Shakhnarovich},
  journal={ArXiv},
  year={2017},
  volume={abs/1605.07648}
}

Gustav Larsson, M. Maire, Gregory Shakhnarovich

Published 2017

Computer Science

ArXiv

We introduce a design strategy for neural network macro-architecture based on self-similarity. Repeated application of a simple expansion rule generates deep networks whose structural layouts are precisely truncated fractals. These networks contain interacting subpaths of different lengths, but do not include any pass-through or residual connections; every internal signal is transformed by a filter and nonlinearity before being seen by subsequent layers. In experiments, fractal networks match… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed