1
کامپیوتر و شبکه::
گرادیان کاهشی تصادفی
return SGD(self.model.parameters(), lr=0.001, momentum=0.99)
For our optimizer, we'll use basic stochastic gradient descent (SGD
;Using SGD is generally considered a safe place to start when it comes to picking an
optimizer; there are some problems that might not work well with SGD, but they're
Empirically, SGD with those values has worked reasonably well for a wide
واژگان شبکه مترجمین ایران
2
برق و الکترونیک::
گرادیان نزولی تصادفی
Stochastic Gradient Descent 117
A good place to start is with a Stochastic Gradient Descent (SGD) classifier, using Scikit-Learn's SGDClassifier class.
This is in part because SGD deals with training instances independently, one at a time (which also makes SGD well suited for online learning), as we will see later.
sgd_clf = SGDClassifier(random_state=42) sgd_clf.fit(X_train, y_train_5)
>>> sgd_clf.predict([some_digit]) array([ True], dtype=bool)
واژگان شبکه مترجمین ایران