What would it look like to add the backprop step as Python too? #36

kwinkunks · 2023-05-11T07:43:48Z

We have the forward pass, which already makes the nice point that the network is a function and the forward pass is cheap... but this does not reflect hyperparams directly, eg how regularization works.

What would it look like to add the training loop as a function as well? Too much?

kwinkunks added enhancement New feature or request help wanted Extra attention is needed question Further information is requested labels May 11, 2023

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

What would it look like to add the backprop step as Python too? #36

What would it look like to add the backprop step as Python too? #36

kwinkunks commented May 11, 2023

What would it look like to add the backprop step as Python too? #36

What would it look like to add the backprop step as Python too? #36

Comments

kwinkunks commented May 11, 2023