Successfully and efficiently training deep multi-layer perceptrons with logistic activation function simply requires initializing the weights with an appropriate negative mean (Q6077039)

From MaRDI portal
Revision as of 20:33, 5 May 2024 by Daniel (talk | contribs) (‎Created claim: Wikidata QID (P12): Q113868229, #quickstatements; #temporary_batch_1714933964039)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
scientific article; zbMATH DE number 7751448
Language Label Description Also known as
English
Successfully and efficiently training deep multi-layer perceptrons with logistic activation function simply requires initializing the weights with an appropriate negative mean
scientific article; zbMATH DE number 7751448

    Statements

    Successfully and efficiently training deep multi-layer perceptrons with logistic activation function simply requires initializing the weights with an appropriate negative mean (English)
    0 references
    0 references
    0 references
    17 October 2023
    0 references
    0 references
    deep neural networks
    0 references
    vanishing gradient
    0 references
    weights initialization
    0 references
    logistic activation function
    0 references
    supervised learning
    0 references
    0 references