University of Pittsburgh

Deepmind Technologies Limited

Sagi Perel

Maxwell Elliot Jaderberg

Timothy James Alexander Harley

Chenjie Gu

David Budden

Valentin Clement Dalibard

Ang Li

Meel Velliste

Pramod Gupta

Andrew S Whitford

Ola Spyra

Andrew Schwartz

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model. A method includes: maintaining a plurality of training sessions; assigning, to each worker of one or more workers, a respective training session of the plurality of training sessions; repeatedly performing operations until meeting one or more termination criteria, the operations comprising: receiving an updated training session from a respective worker of the one or more workers, selecting a second training session, selecting, based on comparing the updated training session and the second training session using a fitness evaluation function, either the updated training session or the second training session as a parent training session, generating a child training session from the selected parent training session, and assigning the child training session to an available worker, and selecting a candidate model to be a trained model for the machine learning model.

Population-based training of machine learning models

A methodology for using cortical signals to control a multi jointed prosthetic device for direct real-time interaction with the physical environment, including improved methods for calibration and training.

Cortical control of a prosthetic device

Growing community of inventors

Pittsburgh, PA, United States of America

Sagi Perel