Skip to main content

1981 | OriginalPaper | Buchkapitel

Loss Functions and Stochastic Approximation

verfasst von : Jack Sklansky, Gustav N. Wassel

Erschienen in: Pattern Classifiers and Trainable Machines

Verlag: Springer New York

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Gradient descent as a technique for finding the minimum of a loss function J(v) was introduced in Section 2.10. Recall that the technique consists of finding the gradient ∇ J(v) and then adjusting the parameter vector v so that the change in v is in the direction of the negative of the gradient.

Metadaten
Titel
Loss Functions and Stochastic Approximation
verfasst von
Jack Sklansky
Gustav N. Wassel
Copyright-Jahr
1981
Verlag
Springer New York
DOI
https://doi.org/10.1007/978-1-4612-5838-4_4

Neuer Inhalt