Leveraging the TensorFlow Keras API

Keras is a deep learning API that wraps around machine learning libraries such as TensorFlow, Theano, and Microsoft Cognitive Toolkit (also known as CNTK). Its popularity as a standalone API stems from the succinct style of the model construction process. As of 2018, TensorFlow added Keras as a high-level API moving forward, and it is now known as tf.keras. Starting with the TensorFlow 2.0 distribution released in 2019, tf.keras has become the official high-level API.

tf.keras excels at modeling sophisticated deep learning architecture that contains long short-term memory (LSTM), gated recurring units (GRUs), and convolutional neural network (CNN) layers. These are considered to be workhorses in current natural language processing (NLP) and computer vision models. It also provides simple and straightforward architecture for simpler deep learning models, such as multilayer perceptrons. In the following example, we are going to use the tf.keras...