Détail de l'auteur
Auteur Vincent VANDENBUSSCHE |
Documents disponibles écrits par cet auteur (1)
Ajouter le résultat dans votre panier Faire une suggestion Affiner la recherche
The Regularization Cookbook : Explore practical recipes to improve the functionality of your ML models / Vincent VANDENBUSSCHE / PACKT PUBLISHING (2023)
Titre : The Regularization Cookbook : Explore practical recipes to improve the functionality of your ML models Type de document : e-book Auteurs : Vincent VANDENBUSSCHE Editeur : PACKT PUBLISHING Année de publication : 2023 ISBN/ISSN/EAN : 9781837634088 Note générale : copyrighted Langues : Anglais (eng) Résumé : Methodologies and recipes to regularize any machine learning and deep learning model using cutting-edge technologies such as stable diffusion, Dall-E and GPT-3 Purchase of the print or Kindle book includes a free PDF eBookKey FeaturesLearn to diagnose the need for regularization in any machine learning modelRegularize different ML models using a variety of techniques and methodsEnhance the functionality of your models using state of the art computer vision and NLP techniquesBook DescriptionRegularization is an infallible way to produce accurate results with unseen data, however, applying regularization is challenging as it is available in multiple forms and applying the appropriate technique to every model is a must. The Regularization Cookbook provides you with the appropriate tools and methods to handle any case, with ready-to-use working codes as well as theoretical explanations. After an introduction to regularization and methods to diagnose when to use it, you’ll start implementing regularization techniques on linear models, such as linear and logistic regression, and tree-based models, such as random forest and gradient boosting. You’ll then be introduced to specific regularization methods based on data, high cardinality features, and imbalanced datasets. In the last five chapters, you’ll discover regularization for deep learning models. After reviewing general methods that apply to any type of neural network, you’ll dive into more NLP-specific methods for RNNs and transformers, as well as using BERT or GPT-3. By the end, you’ll explore regularization for computer vision, covering CNN specifics, along with the use of generative models such as stable diffusion and Dall-E. By the end of this book, you’ll be armed with different regularization techniques to apply to your ML and DL models.What you will learnDiagnose overfitting and the need for regularizationRegularize common linear models such as logistic regressionUnderstand regularizing tree-based models such as XGBoosUncover the secrets of structured data to regularize ML modelsExplore general techniques to regularize deep learning modelsDiscover specific regularization techniques for NLP problems using transformersUnderstand the regularization in computer vision models and CNN architecturesApply cutting-edge computer vision regularization with generative modelsWho this book is forThis book is for data scientists, machine learning engineers, and machine learning enthusiasts, looking to get hands-on knowledge to improve the performances of their models. Basic knowledge of Python is a prerequisite. Nombre d'accès : Illimité En ligne : http://library.ez.neoma-bs.fr/login?url=https://www.scholarvox.com/book/88946108 Permalink : https://cataloguelibrary.neoma-bs.fr/index.php?lvl=notice_display&id=579791
LIBRARY - Campus Rouen
NEOMA Business School
pmb
-
59 Rue Taittinger, 51100 Reims
-
00 33 (0)3 26 77 46 15
Library Campus Reims
-
1 Rue du Maréchal Juin, BP 215
76825 Mont Saint Aignan cedex -
00 33 (0)2 32 82 58 26