Proteins are essential to life, and understanding their structure can facilitate a mechanistic
understanding of their function. Through an enormous experimental effort 1, 2, 3, 4, the …

We adapt the ideas underlying the success of Deep Q-Learning to the continuous action
domain. We present an actor-critic, model-free algorithm based on the deterministic policy …

Protein structures can provide invaluable information, both for reasoning about biological
processes and for enabling interventions such as structure-based drug development or …

The vast majority of missense variants observed in the human genome are of unknown
clinical significance. We present AlphaMissense, an adaptation of AlphaFold fine-tuned on …

Global medium-range weather forecasting is critical to decision-making across many social
and economic domains. Traditional numerical weather prediction uses increased compute …

Deep neural networks (NNs) are powerful black box predictors that have recently achieved
impressive performance on a wide spectrum of tasks. Quantifying predictive uncertainty in …

While the vast majority of well-structured single protein chains can now be predicted to high
accuracy due to the recent AlphaFold [ 1 ] model, the prediction of multi-chain protein …

We consider general theories of a massive spin-2 particle $h_{\mu\nu}$ on a Minkowski
background. A decomposition of $h_{\mu\nu}$ in terms of helicity eigenstates allows us to …

Efficient exploration remains a major challenge for reinforcement learning (RL). Common
dithering strategies for exploration, such as epsilon-greedy, do not carry out temporally-…

For artificial general intelligence (AGI) it would be efficient if multiple users trained the same
giant neural network, permitting parameter reuse, without catastrophic forgetting. PathNet is …