https://esl.proz.com/kudoz/spanish-to-english/mathematics-statistics/6848894-actualizaci%C3%B3n-de-descenso-de-gradiente-estoc%C3%A1stico-calculada.html
This site uses cookies. Some of these cookies are essential to the operation of the site, while others help to improve your experience by providing insights into how the site is being used. For more information, please see the ProZ.com privacy policy.
Cookie settings
PSE
cantera de lajas

Glossary entry

español term or phrase:

actualización de descenso de gradiente estocástico calculada

inglés translation:

calculated update of a stochastic gradient descent

Added to glossary by Robert Copeland
Jul 22, 2020 14:29
4 yrs ago
16 viewers *
español term

actualización de descenso de gradiente estocástico calculada

español al inglés Otros Matemáticas y estadística
Context: El optimizador ADAM se utilizó para entrenar a la red con una tasa de aprendizaje inicial de 0.001. Este algoritmo podría considerarse como una actualización para RMSProp, que ofrece corección de sesgo e impulso. Proporciona tasas de aprendizaje adaptivo para la actualización de descenso de gradiente estocástico calculada desde el primer y segundo momento de los gradientes.
Proposed translations (inglés)
4 calculated update of a stochastic gradient descent
4 -1 updated stochastic gradient descent calculated
Change log

Jul 22, 2020 16:32: philgoddard changed "Field (write-in)" from "General knowledge" to "(none)"

Discussion

Yvonne Gallagher Jul 23, 2020:
@Helena agree with you, the update (of the stochastic gradient descents) is calculated from...

Put it as answer
Helena Chavarria Jul 22, 2020:
FWIW, I read it as 'It provides adaptive learning rates (in order) to update the stochastic gradient descent, which (i.e. the update) is calculated from the first and second moment of the gradients'.

Proposed translations

3 horas
Selected

calculated update of a stochastic gradient descent

Gradient descent is a first-order iterative optimization algorithm for finding a local minimum of a differentiable function. To find a local minimum of a function using gradient descent, we take steps proportional to the negative of the gradient (or approximate gradient) of the function at the current point.
Something went wrong...
4 KudoZ points awarded for this answer.
-1
55 minutos

updated stochastic gradient descent calculated

Stochastic gradient descent (often abbreviated SGD) is an iterative method for optimizing an objective function with suitable smoothness properties (e.g. differentiable or subdifferentiable).
http://en.wikipedia.org/wiki/Stochastic_gradient_descent

I'm not sure why is says "calculada", since the only feminine singular noun is "actualización", but this doesn't affect the translation.
Peer comment(s):
disagree Francois Boye : it's the update that is calculated
2 horas
Yes, that's why I said updated... calculated. Your answer is the same as mine.
Something went wrong...