About
Log in
Log in?
DTU users get better search results including licensed content and discounts on order fees.
Anyone can log in and get personalized features such as favorites, tags and feeds.
DTU Findit
DTU
Close advanced
{{problem}}
By field
Using AND/OR
By author
This tool can help you build boolean queries suitable for doing a broad search for different synonyms or spellings of each word. Start via the drop-down below or just start typing in the search field.
{{ row.typeTitle }}:
(
)
Author:
Khan
remove
Interpreted as:
title:(Approximate AND Inference AND Turns AND Deep AND Networks AND into AND Gaussian AND Processes)
Suggestions: Include records that partially match the query
Previous
1
-
2
of
2
Next
1
Conference paper
Approximate Inference Turns Deep Networks into Gaussian Processes
Deep neural networks (DNN) and Gaussian processes (GP) are two powerful models with several theoretical connections relating them, but the relationship between their training methods is not well understood. In this paper, we show that certain Gaussian posterior approximations for Bayesian DNNs
Year: 2019
Language: English
2
Preprint article
Approximate Inference Turns Deep Networks into Gaussian Processes
Deep neural networks (DNN) and Gaussian processes (GP) are two powerful
models with several theoretical connections relating them, but the relationship
between their training methods is not well understood. In this paper, we show
that certain Gaussian posterior approximations for Bayesian DNNs
Year: 2020
Language: Undetermined
