February 2018
Intermediate to advanced
378 pages
10h 14m
English
Keras is a popular Python package for building deep learning neural networks. It has a user-friendly syntax. It's easy and fast to prototype and build your deep models in. It started as a facade for the Theano symbolic computation library, but with time, it also got a TensorFlow backend and finally became a part of TensorFlow. So now, TensorFlow is a default backend, but you still have an option to switch back to Theano. There are also work-in-progress projects on MXNet and CNTK backends.
Keras contains functions for pre-processing most common data types, which include images, texts, and time series.
CoreML supports convolution and recurrent neural networks built in Keras.
Read now
Unlock full access