June 2020
Intermediate to advanced
382 pages
11h 39m
English
Keras needs a lower-level deep learning library to perform tensor-level manipulations. This lower level deep-learning library is called the backend engine. Possible backend engines for Keras include the following:
TensorFlow (www.tensorflow.org): This is the most popular framework of its kind and is open sourced by Google.
Theona (deeplearning.net/software/theano): This was developed at the MILA lab at Université de Montréal.
Microsoft Cognitive Toolkit (CNTK): This was developed by Microsoft.
The format of this modular deep learning technology stack is shown in the following diagram:

The advantage of this modular ...