Deep neural networks being at the core of deep learning (DL) allow computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art stuff in speech recognition, multimedia (image/audio/video) analytics, NLP, image processing and segmentation, visual object recognition, object detection, and many other domains in life sciences, such as cancer genomics, drug discovery, personalized medicine, and biomedical imaging.
Throughout this book, we have seen how to use JVM-based DL libraries to develop some applications covering these areas. I confess that some projects were not so comprehensive and cannot be deployed commercially but need some extra effort. Nonetheless, showing how to deploy such models was not within...
