class nbla::RMSprop

template<typename T>
class RMSprop : public nbla::Solver

RMSprop.

This is defined as

\[\begin{split} g_t \leftarrow \Delta w_t\\ v_t \leftarrow \gamma v_{t-1} + \left(1 - \gamma \right) g_t^2\\ w_{t+1} \leftarrow w_t - \eta \frac{g_t}{\sqrt{v_t} + \epsilon} \end{split}\]

See also

See the paper linked below for more details. Geoff Hinton Lecture 6a : Overview of mini-batch gradient descent http://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf

Param lr:

\(\eta\) Learning rate.

Param decay:

\(\gamma\) Decay rate.

Param eps:

\(\epsilon\) Tiny factor for avoiding 0-division.

Public Functions

inline virtual float learning_rate()

Set learning rate.