| sgd {CNN} | R Documentation |
stochastic approximation of the gradient descent optimization method for minimizing an objective function
that is written as a sum of differentiable functions. In other words, SGD tries to find minimums or
maximums by iteration.
sgd(batch.size,
learning.rate = 0.01,
momentum = 0.9,
eps = 1E-08,
l2.decay = 0.001);