Put AI to work
June 26-27, 2017: Training
June 27-29, 2017: Tutorials & Conference
New York, NY

AI building AI: How evolutionary algorithms are revolutionizing deep learning

Risto Miikkulainen (Sentient.ai)
11:05am11:45am Wednesday, June 28, 2017
Implementing AI
Location: Murray Hill E/W Level: Intermediate

Prerequisite Knowledge

  • A basic understanding of neural networks

What you'll learn

  • Understand how evolutionary algorithms can be used to effectively train deep networks

Description

As deep learning systems get more complex and their applications get more ambitious, researching and engineering deep learning networks is becoming harder and harder. Sentient Technologies has pioneered a different approach that helps mitigate those difficulties: namely, evolutionary algorithms.

Sentient has built the largest evolutionary algorithm system in the world, scaling to 2 million CPU cores and 4,000 GPUs. Risto Miikkulainen explains how to use massively distributed evolutionary algorithms to evolve the actual architectures of deep networks. It’s AI building AI, and it’s an essential step on the path to industrializing and scaling the application of deep learning.

Photo of Risto Miikkulainen

Risto Miikkulainen

Sentient.ai

Risto Miikkulainen is vice president of research at Sentient Technologies and a professor of computer science at the University of Texas at Austin. His recent research focuses on methods and applications of neuroevolution, as well as neural network models of natural language processing and vision. Risto has published over 370 articles in these research areas and has 16 patents pending. He is an IEEE Fellow and a recipient of the 2017 Gabor Award of the International Neural Network Society. Risto holds an MS in engineering from the Helsinki University of Technology, Finland, and a PhD in computer science from UCLA.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)