[
https://issues.apache.org/jira/browse/SYSTEMML-618?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15278693#comment-15278693
]
Mike Dusenberry commented on SYSTEMML-618:
------------------------------------------
Updates:
* The library is currently written entirely in the DML (R-like) syntax. I am
about to start adding a PyDML version that will become the new main codebase.
I plan to maintain both versions in the same repo, with DML & PyDML versions
co-located in the repo.
* There is early support for (vanilla) RNNs and LSTMs. The plan is to expand
on both of these.
> Deep Learning DML Library
> -------------------------
>
> Key: SYSTEMML-618
> URL: https://issues.apache.org/jira/browse/SYSTEMML-618
> Project: SystemML
> Issue Type: New Feature
> Reporter: Mike Dusenberry
> Assignee: Mike Dusenberry
>
> This issue tracks the creation of an experimental, layers-based library in
> pure PyDML & DML that contains layers with simple forward/backward APIs for
> affine, convolution (start with 2D), max-pooling, non-linearities (relu,
> sigmoid, softmax, etc.), dropout, loss functions, other layers, optimizers,
> and gradient checks.
> *SystemML-NN*:
> [https://github.com/dusenberrymw/systemml-nn|https://github.com/dusenberrymw/systemml-nn]
> _Current status:_
> * Layers:
> ** Core:
> *** Affine
> *** Spatial Convolution
> *** LSTM
> *** Max Pooling
> *** RNN
> ** Nonlinearities:
> *** ReLU
> *** Sigmoid
> *** Softmax
> *** Tanh
> ** Loss:
> *** Cross-entropy loss
> *** L1 loss
> *** L2 loss
> *** Log ("Logistic") loss
> ** Regularization:
> *** Dropout
> *** L1 reg
> *** L2 reg
> * Optimizers:
> ** Adagrad
> ** Adam
> ** RMSprop
> ** SGD
> ** SGD w/ Momentum
> ** SGD w/ Nesterov Momentum
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
