Devine / Pawlus Hands-On Deep Learning with R

A practical guide to designing, building, and improving neural network models using R
1. Auflage 2020
ISBN: 978-1-78899-378-4
Verlag: De Gruyter
Format: EPUB
Kopierschutz: 0 - No protection

E-Book, Englisch, 330 Seiten

No detailed description available for "Hands-On Deep Learning with R".

Autoren/Hrsg.

Devine, Rodger

Pawlus, Michael

Fachgebiete

• Mathematik | Informatik EDV | Informatik Daten / Datenbanken Automatische Datenerfassung, Datenanalyse
• Mathematik | Informatik EDV | Informatik Informatik Theoretische Informatik
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz

Inhaltsverzeichnis

Table of Contents - Machine Learning Basics

- Setting Up R for Deep Learning

- Artificial Neural Networks

- Convolutional Neural Networks for Image Recognition
- Multilayer Perceptron Neural Networks for Signal Detection
- Neural Collaborative Filtering Using Embeddings
- Deep Learning for Natural Language Processing
- Long Short-Term Memory Networks for Stock Forecast
- Generative Adversarial Networks for Face Generation
- Reinforcement Learning for gaming

- Deep Q Learning for Maze Solving

Über Autor(innen)

Devine Rodger:

Rodger Devine is the Associate Dean of External Affairs for Strategy and Innovation at the USC Dornsife College of Letters, Arts, and Sciences. Rodger's portfolio includes advancement operations, BI, leadership annual giving, program innovation, prospect development, and strategic information management. Prior to USC, Rodger served as the Director of Information, Analytics, and Annual Giving at the Michigan Ross School of Business. Rodger brings nearly 20 years of experience in software engineering, IT operations, BI, project management, organizational development, and leadership. Rodger completed his Masters in data science at the University of Michigan and is a doctoral student in the OCL program at the USC Rossier School of Education.Pawlus Michael:

Michael Pawlus is a data scientist at The Ohio State University where he is currently part of the team building of the data science infrastructure for the Advancement department while also leading the implementation of innovative projects there. Prior to this, Michael was a data scientist at the University of Southern California. In addition to this work, Michael has chaired data science education conferences, published articles on the role of data science within fundraising and currently serves on committees where he is focused on providing a wider variety of educational offerings as well as increasing the diversity of content creators in this space. Michael holds degrees from Grand Valley State University and the University of Sheffield.