Search Results for author:
Found 8 papers, 4 papers with code
Learned Force Fields Are Ready For Ground State Catalyst Discovery
We present evidence that learned density functional theory (``DFT'') force fields are ready for ground state catalyst discovery.
Simple GNN Regularisation for 3D Molecular Property Prediction and Beyond
We introduce “Noisy Nodes”, a very simple technique for improved training of GNNs, in which we corrupt the input graph with noise, and add a noise correcting node-level loss.
Initial Structure to Relaxed Energy (IS2RE), Direct
Molecular Property Prediction
+1
Simple GNN Regularisation for 3D Molecular Property Prediction & Beyond
From this observation we derive "Noisy Nodes", a simple technique in which we corrupt the input graph with noise, and add a noise correcting node-level loss.
Ranked #4 on
Initial Structure to Relaxed Energy (IS2RE)
on OC20
Distral: Robust Multitask Reinforcement Learning
Moreover, the proposed learning process is more robust and more stable---attributes that are critical in deep reinforcement learning.
Overcoming catastrophic forgetting in neural networks
The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence.
Ranked #3 on
Continual Learning
on F-CelebA (10 tasks)
The Forget-me-not Process
We introduce the Forget-me-not Process, an efficient, non-parametric meta-algorithm for online probabilistic sequence prediction for piecewise stationary, repeating sources.
Progressive Neural Networks
Learning to solve complex sequences of tasks--while both leveraging transfer and avoiding catastrophic forgetting--remains a key obstacle to achieving human-level intelligence.
Policy Distillation
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-specific) networks and extensive training are needed to achieve good performance.
