Github user avulanov commented on the pull request:
https://github.com/apache/spark/pull/1290#issuecomment-81842046
Hi, @Zehao
Gradient class computes the delta of gradient `dG`, updater class updates
the gradient, simply `G(i+1)=G(i) + r*dG`, where `r` is learning rate. Bias `b`
of the layer works as follows: `y=f(A*x^T+b)`, where `f` is activation
function, `x` is layer input. `A` and `b` are layer parameters or weights.
We are currently working on the more generic interface for the artificial
neural networks, which should be easily extensible with the other layer and
network types: https://github.com/avulanov/spark/tree/ann-interface
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
