Skip to main content
Uber logo

Schedule rides in advance

Reserve a rideReserve a ride

Schedule rides in advance

Reserve a rideReserve a ride
AI

Differentiable Plasticity: A New Method for Learning to Learn

April 10, 2018 / Global
Featured image for Differentiable Plasticity: A New Method for Learning to Learn
Figure 1: An image completion task (each row indicates a separate episode). After being shown three images, the network is given a partial image and must reconstruct the missing part from memory. Non-plastic networks (including LSTMs) cannot solve this task. Source images from the .
Figure 2: A maze exploration task. The agent (yellow square) is rewarded for hitting the reward location (green square) as many times as possible (the agent is teleported to a random location each time it finds the reward). In Episode 1 (left), the agent’s behavior is essentially random. After 300,000 episodes (right), the agent has learnt to memorize the reward location and navigate towards it.
Thomas Miconi

Thomas Miconi

Thomas Miconi is a research scientist at Uber AI Labs.

Jeff Clune

Jeff Clune

Jeff Clune is the former Loy and Edith Harris Associate Professor in Computer Science at the University of Wyoming, a Senior Research Manager and founding member of Uber AI Labs, and currently a Research Team Leader at OpenAI. Jeff focuses on robotics and training neural networks via deep learning and deep reinforcement learning. He has also researched open questions in evolutionary biology using computational models of evolution, including studying the evolutionary origins of modularity, hierarchy, and evolvability. Prior to becoming a professor, he was a Research Scientist at Cornell University, received a PhD in computer science and an MA in philosophy from Michigan State University, and received a BA in philosophy from the University of Michigan. More about Jeff’s research can be found at JeffClune.com

Kenneth O. Stanley

Kenneth O. Stanley

Before joining Uber AI Labs full time, Ken was an associate professor of computer science at the University of Central Florida (he is currently on leave). He is a leader in neuroevolution (combining neural networks with evolutionary techniques), where he helped invent prominent algorithms such as NEAT, CPPNs, HyperNEAT, and novelty search. His ideas have also reached a broader audience through the recent popular science book, Why Greatness Cannot Be Planned: The Myth of the Objective.

Posted by Thomas Miconi, Jeff Clune, Kenneth O. Stanley

Category: