Add learning rate finder

[aptrishu]

A learning rate finder can easily be implemented as shown in https://arxiv.org/abs/1506.01186 I would make a PR if this functionality seems appropriate to add.

[LucasAnders1]

I implemented a simple callback in keras which can be used to find an optimal learning rate. Feel free to use it: https://github.com/LucasAnders1/LearningRateFinder

[saksham219]

Hi this link is broken. Could you provide the correct link? @LucasAnders1

[sachinpuranik99]

@saksham219 https://github.com/LucasAnders1/LearningRateFinder

[WittmannF]

Here's my version: https://gist.github.com/WittmannF/c55ed82d27248d18799e2be324a79473

Three changes were made:

• Number of iterations is automatically inferred as the number of batches (i.e., it will always run over one epoch)
• Set of learning rates are spaced evenly on a log scale (a geometric progression) using np.geospace
• Automatic stop criteria if current_loss > 10 x lowest_loss