Predicting the Outputs of Finite Networks Trained with Noisy Gradients

no code implementations • 28 Sep 2020 • Gadi Naveh, Oded Ben-David, Haim Sompolinsky, Zohar Ringel

A recent line of works studied wide deep neural networks (DNNs) by approximating them as Gaussian Processes (GPs).

Gaussian Processes Image Classification

Predicting the outputs of finite deep neural networks trained with noisy gradients

no code implementations • 2 Apr 2020 • Gadi Naveh, Oded Ben-David, Haim Sompolinsky, Zohar Ringel

A recent line of works studied wide deep neural networks (DNNs) by approximating them as Gaussian Processes (GPs).

Gaussian Processes Image Classification

The role of a layer in deep neural networks: a Gaussian Process perspective

no code implementations • 6 Feb 2019 • Oded Ben-David, Zohar Ringel

Leveraging this correspondence, we derive the Deep Gaussian Layer-wise loss functions (DGLs) which, we believe, are the first supervised layer-wise loss functions which are both explicit and competitive in terms of accuracy.

Gaussian Processes