Skip to Main Content
The Deep Learning with Keras Workshop
book

The Deep Learning with Keras Workshop

by Matthew Moocarme, Mahla Abdolahnejad, Ritesh Bhagwat
July 2020
Intermediate to advanced content levelIntermediate to advanced
496 pages
9h 10m
English
Packt Publishing
Content preview from The Deep Learning with Keras Workshop

5. Improving Model Accuracy

Overview

This chapter introduces the concept of regularization for neural networks. Regularization aims to prevent the model from overfitting the training data during the training process and provides more accurate results when the model is tested on new unseen data. You will learn to utilize different regularization techniques—L1 and L2 regularization and dropout regularization—to improve model performance. Regularization is an important component as it prevents neural networks from overfitting the training data and helps us build robust, accurate models that perform well on new, unseen data. By the end of this chapter, you will be able to implement a grid search and random search in scikit-learn and find the ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

The Applied TensorFlow and Keras Workshop

The Applied TensorFlow and Keras Workshop

Harveen Singh Chadha, Luis Capelo
Keras 2.x Projects

Keras 2.x Projects

Giuseppe Ciaburro
Trends in Deep Learning Methodologies

Trends in Deep Learning Methodologies

Vincenzo Piuri, Sandeep Raj, Angelo Genovese, Rajshree Srivastava
Intelligent Data Analysis for Biomedical Applications

Intelligent Data Analysis for Biomedical Applications

D. Jude Hemanth, Deepak Gupta, Valentina Emilia Balas

Publisher Resources

ISBN: 9781800562967Supplemental Content