Yoshua Bengio, Devansh Arpit, Aaron Courville, Min Lin, Nasim Rahaman, Fred Hamprecht, Felix Draxler, Aristide Baratin
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Neural networks are known to be a class of highly expressive functions able to fit even random inputoutput mappings with 100% accuracy. In this work we present properties of neural networks that complement this aspect of expressivity. By using tools from Fourier analysis, we highlight a learning bias of deep networks towards low frequency functions -i.e. functions that vary globally without local fluctuations -which manifests itself as a frequency-dependent learning speed. Intuitively, this property is in line with the observation that over-parameterized networks prioritize learning simple patterns that generalize across data samples. We also investigate the role of the shape of the data manifold by presenting empirical and theoretical evidence that, somewhat counter-intuitively, learning higher frequencies gets easier with increasing manifold complexity.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1806.08734")
get_code_for_paper("1806.08734")
have("1806.08734")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1806.08734.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1806.08734)
Connect an agent — have() is free.