The NeurIPS '18 Competition
From Machine Learning to Intelligent Conversations
Editors: Escalera, Sergio, Hebrick, Ralf (Eds.)
- The NeurIPS Competition evaluates the performance of an entire system rather than a well-isolated task or component, enabling the evaluation of the feasibility of an algorithm extracting key predictive signal from a dataset, as well as the implementation in a running production system
- Presents a stronger focus on live competitions, including the competition finals at the NeurIPS 2018 conference
- New data sets and top winning solutions are presented
Buy this book
- About this book
-
This volume presents the results of the Neural Information Processing Systems Competition track at the 2018 NeurIPS conference. The competition follows the same format as the 2017 competition track for NIPS. Out of 21 submitted proposals, eight competition proposals were selected, spanning the area of Robotics, Health, Computer Vision, Natural Language Processing, Systems and Physics.
Competitions have become an integral part of advancing state-of-the-art in artificial intelligence (AI). They exhibit one important difference to benchmarks: Competitions test a system end-to-end rather than evaluating only a single component; they assess the practicability of an algorithmic solution in addition to assessing feasibility.
The eight run competitions aim at advancing the state of the art in deep reinforcement learning, adversarial learning, and auto machine learning, among others, including new applications for intelligent agents in gaming and conversational settings, energy physics, and prosthetics.
Recommended for you
Bibliographic Information
- Bibliographic Information
-
- Book Title
- The NeurIPS '18 Competition
- Book Subtitle
- From Machine Learning to Intelligent Conversations
- Editors
-
- Sergio Escalera
- Ralf Hebrick
- Series Title
- The Springer Series on Challenges in Machine Learning
- Copyright
- 2020
- Publisher
- Springer International Publishing
- Copyright Holder
- Springer Nature Switzerland AG
- eBook ISBN
- 978-3-030-29135-8
- DOI
- 10.1007/978-3-030-29135-8
- Hardcover ISBN
- 978-3-030-29134-1
- Series ISSN
- 2520-131X
- Edition Number
- 1
- Number of Pages
- IX, 342
- Number of Illustrations
- 130 b/w illustrations
- Topics
