Modern Deep Learning for Tabular Data : Novel Approaches to Common Modeling Problems

Modern Deep Learning for Tabular Data Novel Approaches to Common Modeling Problems

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...

Full description

Bibliographic Details
Other Authors: Ye, Andre, author (author), Wang, Zi'an, author
Format: eBook
Language:Inglés
Published: Berkeley, CA : Apress 2023.
Edition:1st ed. 2023.
Subjects:
Machine learning.
Mathematical models.
See on Biblioteca Universitat Ramon Llull:https://discovery.url.edu/permalink/34CSUC_URL/1im36ta/alma991009755097706719
Table of Contents:
  • Part 1: Machine Learning and Tabular Data
  • Chapter 1 – Introduction to Machine Learning
  • Chapter 2 – Data Tools
  • Part 2: Applied Deep Learning Architectures
  • Chapter 3 – Artificial Neural Networks
  • Chapter 4 – Convolutional Neural Networks
  • Chapter 5 – Recurrent Neural Networks
  • Chapter 6 – Attention Mechanism
  • Chapter 7 – Tree-based Neural Networks
  • Part 3: Deep Learning Design and Tools
  • Chapter 8 – Autoencoders
  • Chapter 9 – Data Generation
  • Chapter 10 – Meta-optimization
  • Chapter 11 – Multi-model arrangement
  • Chapter 12 – Deep Learning Interpretability
  • Appendix A.

Similar Items