Presented By O’Reilly and Intel Nervana
Put AI to work
September 17-18, 2017: Training
September 18-20, 2017: Tutorials & Conference
San Francisco, CA

Evolving neural networks through neuroevolution

Kenneth Stanley (Uber AI Labs | University of Central Florida)
11:55am–12:35pm Wednesday, September 20, 2017
Implementing AI
Location: Imperial B Level: Beginner
Secondary topics:  Algorithms, Deep learning, Tools and frameworks, Transportation and autonomous vehicles
Average rating: ****.
(4.62, 8 ratings)

Prerequisite Knowledge

  • A general understanding of using algorithms for deep learning

What you'll learn

  • Understand the basics of the field of neuroevolution, including motivation for the field, leading algorithms, major applications, software platforms, top research questions, broader implications, and how to get started


Kenneth Stanley offers an overview of the field of neuroevolution, an emerging paradigm for training neural networks through evolutionary principles that has grown up alongside more conventional deep learning. While deep learning focuses on how brain-like structures in computers can learn, neuroevolution addresses how they evolve in the first place, from their architectures to their intrinsic learning dynamics. As in the broader field of deep learning, increases in available computation have led to a renaissance in potential applications of neuroevolution, some of which complement more conventional techniques by offering a path to novel architectures, while others reveal intriguing alternative systems of incentives for learning (even when a gradient is not available).

Neuroevolution offers a rich and unique history of exploring creative and divergent algorithms. Kenneth introduces key algorithms, explains their history and motivations, and shares insight into the kinds of applications they enable. Along the way, he touches on available platforms and software packages and potential links to other deep learning frameworks.

Photo of Kenneth Stanley

Kenneth Stanley

Uber AI Labs | University of Central Florida

Kenneth O. Stanley is an associate professor in the Department of Computer Science at the University of Central Florida, where he is the director of the evolutionary complexity research group, and a senior research scientist at Uber AI Labs, which he joined through the acquisition of his company, Geometric Intelligence Inc. Kenneth is an inventor of the Neuroevolution of Augmenting Topologies (NEAT), HyperNEAT, and novelty search neuroevolution algorithms for evolving complex artificial neural networks. His main research contributions are in neuroevolution (i.e., evolving neural networks), generative and developmental systems (GDS), nonobjective search, machine learning for video games, and interactive evolution. He is also a coauthor of the popular science book Why Greatness Cannot Be Planned: The Myth of the Objective (Springer) and has spoken widely on its subject. Kenneth has won best paper awards for his work on NEAT, NERO, NEAT Drummer, FSMC, HyperNEAT, ES-HyperNEAT, adaptive HyperNEAT, novelty search, Galactic Arms Race, and NA-IEC. He is an associate editor of IEEE Transactions on Computational Intelligence and AI in Games and the Evolutionary Robotics section of Frontiers in Robotics and AI.