Modern deep learning for tabular data: novel approaches to common modeling problems
- New York Apress 2023
- xxviii, 842 p.
Table of contents: Front Matter Pages i-xxviii Download chapter PDF Machine Learning and Tabular Data Front Matter Pages 1-1 Download chapter PDF Classical Machine Learning Principles and Methods Andre Ye, Zian Wang Pages 3-93 Data Preparation and Engineering Andre Ye, Zian Wang Pages 95-179 Applied Deep Learning Architectures Front Matter Pages 181-181 Download chapter PDF Neural Networks and Tabular Data Andre Ye, Zian Wang Pages 183-258 Applying Convolutional Structures to Tabular Data Andre Ye, Zian Wang Pages 259-378 Applying Recurrent Structures to Tabular Data Andre Ye, Zian Wang Pages 379-450 Applying Attention to Tabular Data Andre Ye, Zian Wang Pages 451-548 Tree-Based Deep Learning Approaches Andre Ye, Zian Wang Pages 549-598 Deep Learning Design and Tools Front Matter Pages 599-599 Download chapter PDF Autoencoders Andre Ye, Zian Wang Pages 601-680 Data Generation Andre Ye, Zian Wang Pages 681-710 Meta-optimization Andre Ye, Zian Wang Pages 711-752 Multi-model Arrangement Andre Ye, Zian Wang Pages 753-770 Neural Network Interpretability Andre Ye, Zian Wang Pages 771-792
Deep learning is one of the most powerful tools in the modern artificial intelligence landscape. While having been predominantly applied to highly specialized image, text, and signal datasets, this book synthesizes and presents novel deep learning approaches to a seemingly unlikely domain – tabular data. Whether for finance, business, security, medicine, or countless other domain, deep learning can help mine and model complex patterns in tabular data – an incredibly ubiquitous form of structured data.
Part I of the book offers a rigorous overview of machine learning principles, algorithms, and implementation skills relevant to holistically modeling and manipulating tabular data. Part II studies five dominant deep learning model designs – Artificial Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks, Attention and Transformers, and Tree-Rooted Networks – through both their ‘default’ usage and their application to tabular data. Part III compounds the power of the previously covered methods by surveying strategies and techniques to supercharge deep learning systems: autoencoders, deep data generation, meta-optimization, multi-model arrangement, and neural network interpretability. Each chapter comes with extensive visualization, code, and relevant research coverage.
Modern Deep Learning for Tabular Data is one of the first of its kind – a wide exploration of deep learning theory and applications to tabular data, integrating and documenting novel methods and techniques in the field. This book provides a strong conceptual and theoretical toolkit to approach challenging tabular data problems