How to Implement in Regression
Abstract
In this chapter, we illustrate how to implement a Deep Neural Network (DNN) in regression analysis. A DNN has several components that construct its multi-layer structure to achieve a strong functional representation. The whole training process involves quite a few hyperparameters to be fine-tuned. A numerical example is provided to approximate a non-linear function with DNN . For hyperparameter tuning, we first focus on each univariate parameter and then jointly optimize all hyperparameters of interest. Satisfactory performance of DNN is achieved in both the training and validation datasets.
Fields of Study & Subjects
Neural Networks and Applications
Machine Learning and ELM
Stochastic Gradient Optimization Techniques
Publication details
- Journal / source
- Chapman & Hall/CRC eBooks
- Pages
- 10–20
- Publication date
- 19 January 2026
- Language
- EN
- Document type
- Book chapter