Search icon CANCEL
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
The Deep Learning Architect's Handbook

You're reading from   The Deep Learning Architect's Handbook Build and deploy production-ready DL solutions leveraging the latest Python techniques

Arrow left icon
Product type Paperback
Published in Dec 2023
Publisher Packt
ISBN-13 9781803243795
Length 516 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Author (1):
Arrow left icon
Ee Kin Chin Ee Kin Chin
Author Profile Icon Ee Kin Chin
Ee Kin Chin
Arrow right icon
View More author details
Toc

Table of Contents (25) Chapters Close

Preface 1. Part 1 – Foundational Methods
2. Chapter 1: Deep Learning Life Cycle FREE CHAPTER 3. Chapter 2: Designing Deep Learning Architectures 4. Chapter 3: Understanding Convolutional Neural Networks 5. Chapter 4: Understanding Recurrent Neural Networks 6. Chapter 5: Understanding Autoencoders 7. Chapter 6: Understanding Neural Network Transformers 8. Chapter 7: Deep Neural Architecture Search 9. Chapter 8: Exploring Supervised Deep Learning 10. Chapter 9: Exploring Unsupervised Deep Learning 11. Part 2 – Multimodal Model Insights
12. Chapter 10: Exploring Model Evaluation Methods 13. Chapter 11: Explaining Neural Network Predictions 14. Chapter 12: Interpreting Neural Networks 15. Chapter 13: Exploring Bias and Fairness 16. Chapter 14: Analyzing Adversarial Performance 17. Part 3 – DLOps
18. Chapter 15: Deploying Deep Learning Models to Production 19. Chapter 16: Governing Deep Learning Models 20. Chapter 17: Managing Drift Effectively in a Dynamic Environment 21. Chapter 18: Exploring the DataRobot AI Platform 22. Chapter 19: Architecting LLM Solutions 23. Index 24. Other Books You May Enjoy

Evaluating the bias and fairness of a deep learning model

In this practical example, we will be exploring the infamous real-world use case of face recognition. This practical example will be leveraged for the practical implementation of bias mitigation in the next section. The basis of face recognition is to generate feature vectors that can be used to carry out KNN-based classification so that new faces don’t need to undergo additional network training. In this example, we will be training a classification model and evaluating it using traditional classification accuracy-based metrics; we won’t be demonstrating the recognition part of the use case, which allows us to handle unknown facial identity classes.

The goal here is to ensure that the resulting facial classification model has low gender bias. We will be using a publicly available facial dataset called BUPT-CBFace-50, which has a diverse coverage of facial images that have different facial expressions, poses...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at €18.99/month. Cancel anytime