Summary

In this chapter, you began your journey into creating ANNs in TensorFlow. You saw how simple it is to create regression and classification models by utilizing Keras layers. Keras layers are distinct classes that exist in a separate library that uses TensorFlow in the backend. Due to their popularity and ease of use, they are now included in TensorFlow and can be called in the same way as any other TensorFlow class.

You created ANNs with fully connected layers, varying layers, beginning with an ANN that resembles a linear regression algorithm, which is equivalent to a single-layer ANN. Then, you added layers to your ANN and added activation functions to the output of the layers. Activation functions can be used to determine whether a unit is fired or can be used to bind the value of the output from a given unit. Regression models aim to predict a continuous variable from the data provided. In the exercises and activities throughout this chapter, you attempted to predict...