English | 2022 | ISBN: 9781633439481 | 455 pages | PDF,EPUB | 25.46 MB

Many machine learning problems are too complex to be resolved by a single model or algorithm. Ensemble machine learning trains a group of diverse machine learning models to work together to solve a problem. By aggregating their output, these ensemble models can flexibly deliver rich and accurate results. Ensemble Methods for Machine Learning is a guide to ensemble methods with proven records in data science competitions and real-world applications. Learning from hands-on case studies, you'll develop an under-the-hood understanding of foundational ensemble learning algorithms to deliver accurate, performant models.

about the technology

Ensemble machine learning lets you make robust predictions without needing the huge datasets and processing power demanded by deep learning. It sets multiple models to work on solving a problem, combining their results for better performance than a single model working alone. This "wisdom of crowds" approach distils information from several models into a set of highly accurate results.

about the book

In Ensemble Methods for Machine Learning you'll learn to implement the most important ensemble machine learning methods from scratch. Each chapter contains a new case study, taking you hands-on with a fully functioning ensemble method for medical diagnosis, sennt analysis, handwriting classification, and more. There's no complex math or theory—each method is taught in a practical and visuals-first manner. Best of all, all code is provided in Jupyter notebooks for your easy expentation! By the you're done, you'll know the benefits, limitations, and practical methods of applying ensemble machine learning to real-world data, and be ready to build more explainable ML systems.

search inside this book

what's inside

Bagging, boosting, and gradient boosting

Methods for classification, regression, clustering, and recommendations

Sophisticated off-the-shelf ensemble implementations

Feature eeering and ensemble diversity

Interpretability and explainability for ensemble methods

Human-in-the-loop methods

about the reader

For Python programmers with machine learning experience.

about the author

Gautam Kunapuli has over 15 years of experience in academia and the machine learning industry. He has developed several novel algorithms for diverse application domains including social network analysis, text and natural language processing, behavior mining, educational data mining and biomedical applications. He has also published papers exploring ensemble methods in relational domains and with imbalanced data.