Controlling Level of Unconsciousness by Titrating Propofol with Deep Reinforcement Learning

no code implementations • 27 Aug 2020 • Gabe Schamberg, Marcus Badgeley, Emery N. Brown

We use the cross-entropy method to train a deep neural network to map an observed anesthetic state to a probability of infusing a fixed propofol dosage.

reinforcement-learning Reinforcement Learning (RL)

Wide and deep volumetric residual networks for volumetric image classification

no code implementations • 18 Sep 2017 • Varun Arvind, Anthony Costa, Marcus Badgeley, Samuel Cho, Eric Oermann

3D shape models that directly classify objects from 3D information have become more widely implementable.

3D Object Classification Classification +3