Apple's new iOS CoreML inference engine supports Keras models!
Developers will be able to design and train model using Keras and then convert the architecture to run on the CoreML engine. I suppose you can run TensorFlow models too if you designed them w/ Keras.
Cool that the file format is officially specified as a Protocol Buffer: <a href="https://developer.apple.com/documentation/coreml/converting_trained_models_to_core_ml" rel="nofollow">https://developer.apple.com/documentation/coreml/converting_...</a> (bottom of page)
"BNNS does not do training, however. Its purpose is to provide very high performance inference on already trained neural networks." :(<p><a href="https://developer.apple.com/documentation/accelerate/bnns" rel="nofollow">https://developer.apple.com/documentation/accelerate/bnns</a>
"Core ML is optimized for on-device performance, which minimizes memory footprint and power consumption."<p>This is major, if they have managed to achieve it reasonably. But before opening a Sekt, I want to see some benchmarks. :)
Lots of options to explore, but no reinforcement learning yet.<p>Also, some converted Core ML Models ready to use here: developer.apple.com/machine-learning