The NIPS '17 Competition: Building Intelligent Systems
Editors: Escalera, Sergio, Weimer, Markus (Eds.)
Free Preview- Offers new challenges and methods on reinforcement learning and deep reinforcement learning applied to human body motion and intelligent conversational settings
- Discusses machine learning methods for classifying clinically actionable genetic mutations
- Provides challenges and methods on adversarial learning applied to attacks and defenses
- Presents deep learning applied to transfer knowledge in art
Buy this book
- About this book
-
This book summarizes the organized competitions held during the first NIPS competition track. It provides both theory and applications of hot topics in machine learning, such as adversarial learning, conversational intelligence, and deep reinforcement learning.
Rigorous competition evaluation was based on the quality of data, problem interest and impact, promoting the design of new models, and a proper schedule and management procedure. This book contains the chapters from organizers on competition design and from top-ranked participants on their proposed solutions for the five accepted competitions: The Conversational Intelligence Challenge, Classifying Clinically Actionable Genetic Mutations, Learning to Run, Human-Computer Question Answering Competition, and Adversarial Attacks and Defenses.
- Table of contents (13 chapters)
-
-
Introduction to NIPS 2017 Competition Track
Pages 1-23
-
The First Conversational Intelligence Challenge
Pages 25-46
-
ConvAI Dataset of Topic-Oriented Human-to-Chatbot Dialogues
Pages 47-57
-
A Talker Ensemble: The University of Wroclaw’s Entry to the NIPS 2017 Conversational Intelligence Challenge
Pages 59-77
-
Multi-view Ensemble Classification for Clinically Actionable Genetic Mutations
Pages 79-99
-
Table of contents (13 chapters)
Recommended for you

Bibliographic Information
- Bibliographic Information
-
- Book Title
- The NIPS '17 Competition: Building Intelligent Systems
- Editors
-
- Sergio Escalera
- Markus Weimer
- Series Title
- The Springer Series on Challenges in Machine Learning
- Copyright
- 2018
- Publisher
- Springer International Publishing
- Copyright Holder
- Springer International Publishing AG, part of Springer Nature
- eBook ISBN
- 978-3-319-94042-7
- DOI
- 10.1007/978-3-319-94042-7
- Hardcover ISBN
- 978-3-319-94041-0
- Softcover ISBN
- 978-3-030-06867-7
- Series ISSN
- 2520-131X
- Edition Number
- 1
- Number of Pages
- X, 287
- Number of Illustrations
- 85 b/w illustrations
- Topics