0.9.0

Deeplearning4J
Workspaces feature added (faster training performance + less memory) Link​
SharedTrainingMaster added for Spark network training (improved performance) Link 1, Link 2​
ParallelInference added - wrapper that server inference requests using internal batching and queues  Link​
ParallelWrapper now able to work with gradients sharing, in addition to existing parameters averaging mode Link​
VPTree performance significantly improved
CacheMode network configuration option added - improved CNN and LSTM performance at the expense of additional memory use Link​
LSTM layer added, with CuDNN support Link (Note that the existing GravesLSTM implementation does not support CuDNN)
New native model zoo with pretrained ImageNet, MNIST, and VGG-Face weights Link​
Convolution performance improvements, including activation caching
Custom/user defined updaters are now supported Link​
Evaluation improvements
EvaluationBinary, ROCBinary classes added: for evaluation of binary multi-class networks (sigmoid + xent output layers) Link​
Evaluation and others now have G-Measure and Matthews Correlation Coefficient support; also macro + micro-averaging support for Evaluation class metrics Link​
ComputationGraph and SparkComputationGraph evaluation convenience methods added (evaluateROC, etc)
ROC and ROCMultiClass support exact calculation (previous: thresholded calculation was used) Link​
ROC classes now support area under precision-recall curve calculation; getting precision/recall/confusion matrix at specified thresholds (via PrecisionRecallCurve class) Link​
RegressionEvaluation, ROCBinary etc now support per-output masking (in addition to per-example/per-time-step masking)
EvaluationCalibration added (residual plots, reliability diagrams, histogram of probabilities) Link 1 Link 2​
Evaluation and EvaluationBinary: now supports custom classification threshold or cost array Link​
Optimizations: updaters, bias calculation
Network memory estimation functionality added. Memory requirements can be estimated from configuration without instantiating networks Link 1 Link 2​
New loss functions:
Mixture density loss function Link​
F-Measure loss function Link​
ND4J
Workspaces feature added Link​
Native parallel sort was added
New ops added: SELU/SELUDerivative, TAD-based comparisons, percentile/median, Reverse, Tan/TanDerivative, SinH, CosH, Entropy, ShannonEntropy, LogEntropy, AbsoluteMin/AbsoluteMax/AbsoluteSum, Atan2
New distance functions added: CosineDistance, HammingDistance, JaccardDistance
DataVec
MapFileRecordReader and MapFileSequenceRecordReader added Link 1 Link 2​
Spark: Utilities to save and load JavaRDD<List<Writable>> and JavaRDD<List<List<Writable>> data to Hadoop MapFile and SequenceFile formats Link​
TransformProcess and Transforms now support NDArrayWritables and NDArrayWritable columns
Multiple new Transform classes
Arbiter
Arbiter UI: Link​
UI now uses Play framework, integrates with DL4J UI (replaces Dropwizard backend). Dependency issues/clashing versions fixed.
Supports DL4J StatsStorage and StatsStorageRouter mechanisms (FileStatsStorage, Remote UI via RemoveUIStatsStorageRouter)
General UI improvements (additional information, formatting fixes)
0.9.1
0.8.0
Last modified 1yr ago