Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes

Roman Novak, L. X., Lee, J., Bahri, Y., Yang, G., & Abolafia, D. (2018). Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes.

Type

Unclassified

Intellectual base

Unclassified

Year

2018

Link

no authoritative link yet

Cited by

1 citation across 1 artifact.

Domain-specific

• Large width limits of neural networks
  • … sequence, width parameter, initialization law and variance scaling, depth regime, optimizer and learning-rate scaling, convergence mode, order of limits, and finite-width error are explicit. to An applied instance preserves the same invariant under a changed scale, notation, jurisdiction, dataset, or implementation..

Verification

This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.

Registry ID ref:de0b591e0fe4 · see in the full table