The NIPS '17 Competition: Building Intelligent Systems

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.

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