From 2016 to 2018, I led development of the neural network framework, which encompassed 50+ functions and objects. Since version 10.3 it has been part of the core Mathematica language. It covers a wide range of state-of-the-art deep learning functionality, in an interface that is extremely easy for scientists and engineers to use, rivaling and exceeding the ease-of-use of libraries like Keras.
One notable use of the framework was to replace the filter-bank based gravitional wave detectors used by the LIGO project with convolutional neural networkswww.youtube.com.
To find out more, you can read the extensive online documentation: a comprehensive suite of tutorialsreference.wolfram.com is available, along with a guide pagereference.wolfram.com summarizing the relevant symbols. A good video overview about the framework can be found herewww.youtube.com. Click below to download the poster I made for the RLSS describing some of the benefits of the framework: