TensorFlow Developer Certificate Guide

13

Time Series, Sequences, and Prediction with TensorFlow

Welcome to the final chapter of our journey with TensorFlow. In the last chapter we examined how to build time series models using DNNs along with some simple statistical methods. Here, we will extend our learning by exploring advanced architectures such as CNNs, RNNs, LSTMs, CNN-LSTMs architectures. Also, we will see how to integrate in-built learning rate schedules from TensorFlow into our workflow to dynamically adjust the model’s learning rate during our modeling process. We will also see how to apply custom learning rate schedulers to find the optimal learning rate when building models.

Next, we will discuss Lambda layers and how these arbitrary layers can be applied in our model ...