0.7.2

  • Added variational autoencoder Link

  • Activation function refactor

    • Activation functions are now an interface Link

    • Configuration now via enumeration, not via String (see examples - Link)

    • Custom activation functions now supported Link

    • New activation functions added: hard sigmoid, randomized leaky rectified linear units (RReLU)

  • Multiple fixes/improvements for Keras model import

  • Added P-norm pooling for CNNs (option as part of SubsamplingLayer configuration)

  • Iteration count persistence: stored/persisted properly in model configuration + fixes to learning rate schedules for Spark network training

  • LSTM: gate activation function can now be configured (previously: hard-coded to sigmoid)

  • UI:

    • Added Chinese translation

    • Fixes for UI + pretrain layers

    • Added Java 7 compatible stats collection compatibility Link

    • Improvements in front-end for handling NaNs

    • Added UIServer.stop() method

    • Fixed score vs. iteration moving average line (with subsampling)

  • Solved Jaxb/Jackson issue with Spring Boot based applications

  • RecordReaderDataSetIterator now supports NDArrayWritable for the labels (set regression == true; used for multi-label classification + images, etc)

0.7.1 -> 0.7.2 Transition Notes

  • Activation functions (built-in): now specified using Activation enumeration, not String (String-based configuration has been deprecated)