
Автор: Peng Liu
Издательство: Manning Publications
Год: 2022
Страниц: 323
Язык: английский
Формат: pdf, epub
Размер: 18.0 MB
Make your Deep Learning models more generalized and adaptable! These practical regularization techniques improve training efficiency and help avoid overfitting errors. Regularization in Deep Learning delivers practical techniques to help you build more general and adaptable deep learning models. It goes beyond basic techniques like data augmentation and explores strategies for architecture, objective function, and optimization. You’ll turn regularization theory into practice using PyTorch, following guided implementations that you can easily adapt and customize for your own model’s needs. Along the way, you’ll get just enough of the theory and mathematics behind regularization to understand the new research emerging in this important area. Deep learning models that generate highly accurate results on their training data can struggle with messy real-world test datasets. For data scientists, Machine Learning engineers, and researchers with basic model development experience.