Chapter 6
Fully Connected Networks Applied to Regression
In Chapter 5, “Toward DL: Frameworks and Network Tweaks,” we introduced several activation functions that can be used for hidden units in the network. In this chapter, we describe a couple of alternative output units and describe the problem types for which they are suitable. In addition, we introduce you to another dataset known as the Boston Housing dataset (Harrison and Rubinfeld, 1978).
The code example in this chapter will apply a deep neural network (DNN) to the Boston Housing dataset to predict home values based on a number of different variables and compare it with a simpler model. Predicting a home value is a different type of problem than the classification problems that we have ...
Get Learning Deep Learning: Theory and Practice of Neural Networks, Computer Vision, NLP, and Transformers using TensorFlow now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
