papers

Publications (9)

cond-mat.mtrl-sci2022

Learned Force Fields Are Ready For Ground State Catalyst Discovery

Michael Schaarschmidt, Morgane Riviere, Alex M. Ganose +6

We present evidence that learned density functional theory (``DFT'') force fields are ready for ground state catalyst discovery. Our key finding is that relaxation using forces fro…

cs.LG2017

Distral: Robust Multitask Reinforcement Learning

Yee Whye Teh, Victor Bapst, Wojciech Marian Czarnecki +5

Most deep reinforcement learning algorithms are data inefficient in complex and rich environments, limiting their applicability to many scenarios. One direction for improving data…

cs.LG2016

Policy Distillation

Andrei A. Rusu, Sergio Gomez Colmenarejo, Caglar Gulcehre +6

Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specif…

cond-mat.mes-hall2010

Hot Charge Transfer States and Charge Generation in Donor Acceptor Blends

James Kirkpatrick

In an organic blend the vibrational normal mode excited by exciton splitting is the same as the one coupled to charge hopping. Excess driving force for exciton splitting can theref…

cs.LG2017

Overcoming catastrophic forgetting in neural networks

James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz +11

The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Neural networks are not, in general, capable of this and it has been wi…

cs.LG2022

Simple GNN Regularisation for 3D Molecular Property Prediction & Beyond

Jonathan Godwin, Michael Schaarschmidt, Alexander Gaunt +5

In this paper we show that simple noise regularisation can be an effective way to address GNN oversmoothing. First we argue that regularisers addressing oversmoothing should both p…