Search

Demis Hassabis lauds Garry Kasparov's account of battling supercomputer Deep Blue.

AlphaFold 3 has a substantially updated architecture that is capable of predicting the joint structure of complexes including proteins, nucleic acids, small molecules, ions and modified residues with greatly improved accuracy over many previous specialized tools.

AlphaFold predicts protein structures with an accuracy competitive with experimental structures in the majority of cases using a novel deep learning architecture.

AlphaFold is used to predict the structures of almost all of the proteins in the human proteome—the availability of high-confidence predicted structures could enable new avenues of investigation from a structural perspective.

A recurrent, transformer-based neural network, called AlphaQubit, learns high-accuracy error decoding to suppress the errors that occur in quantum systems, opening the prospect of using neural-network decoders for real quantum hardware.

In modern football games, data-driven analysis serves as a key driver in determining tactics. Wang, Veličković, Hennes et al. develop a geometric deep learning algorithm, named TacticAI, to solve high-dimensional learning tasks over corner kicks and suggest tactics favoured over existing ones 90% of the time.

A scheme for watermarking the text generated by large language models shows high text quality preservation and detection accuracy and low latency, and is feasible in large-scale-production settings.

AlphaStar uses a multi-agent reinforcement learning algorithm and has reached Grandmaster level, ranking among the top 0.2% of human players for the real-time strategy game StarCraft II.

 Artificial intelligence goes beyond the current state of the art by discovering unknown, faster sorting algorithms as a single-player game using a deep reinforcement learning agent. These algorithms are now used in the standard C++ sort library.

AlphaFold predicts the distances between pairs of residues, is used to construct potentials of mean force that accurately describe the shape of a protein and can be optimized with gradient descent to predict protein structures.

Analyses of single-cell recordings from mouse ventral tegmental area are consistent with a model of reinforcement learning in which the brain represents possible future rewards not as a single mean of stochastic outcomes, as in the canonical model, but instead as a probability distribution.

A reinforcement learning approach based on AlphaZero is used to discover efficient and provably correct algorithms for matrix multiplication, finding faster algorithms for a variety of matrix sizes.

A framework through which machine learning can guide mathematicians in discovering new conjectures and theorems is presented and shown to yield mathematical insight on important open problems in different areas of pure mathematics.

Little is known about the brain’s computations that enable the recognition of faces. Here, the authors use unsupervised deep learning to show that the brain disentangles faces into semantically meaningful factors, like age or the presence of a smile, at the single neuron level.

A newly designed control architecture uses deep reinforcement learning to learn to command the coils of a tokamak, and successfully stabilizes a wide variety of fusion plasma configurations.

A reinforcement-learning algorithm that combines a tree-based search with a learned model achieves superhuman performance in high-performance planning and visually complex domains, without any knowledge of their underlying dynamics.

In individuals diagnosed with age-related macular degeneration in one eye, a deep learning model can predict progression to the ‘wet’, sight-threatening form of the disease in the second eye within a 6-month time frame.

An artificial intelligence (AI) system performs as well as or better than radiologists at detecting breast cancer from mammograms, and using a combination of AI and human inputs could help to improve screening efficiency.

Humans and other mammals are prodigious learners, partly because they also ‘learn how to learn’. Wang and colleagues present a new theory showing how learning to learn may arise from interactions between prefrontal cortex and the dopamine system.

Starting from zero knowledge and without human data, AlphaGo Zero was able to teach itself to play Go and to develop novel strategies that provide new insights into the oldest of games.

A novel deep learning architecture performs device-independent tissue segmentation of clinical 3D retinal images followed by separate diagnostic classification that meets or exceeds human expert clinical diagnoses of retinal disease.

AlphaFold is a neural-network-based approach to predicting protein structures with high accuracy. We describe how it works in general terms and discuss some anticipated impacts on the field of structural biology.

A ‘differentiable neural computer’ is introduced that combines the learning capabilities of a neural network with an external memory analogous to the random-access memory in a conventional computer.

A computer Go program based on deep neural networks defeats a human professional player to achieve one of the grand challenges of artificial intelligence.

Fung et al. show that participants’ trait anxiety is associated with earlier escape decisions when facing slowly approaching threats. Anxiety correlates with task-driven blood-oxygen-level-dependent activity in the cognitive fear circuits.

A deep learning approach that predicts the risk of acute kidney injury may help to identify patients at risk of health deterioration within a time window that enables early treatment.

An artificial agent is developed that learns to play a diverse range of classic Atari 2600 computer games directly from sensory experience, achieving a performance comparable to that of an expert human player; this work paves the way to building general-purpose learning algorithms that bridge the divide between perception and action.

Grid-like representations emerge spontaneously within a neural network trained to self-localize, enabling the agent to take shortcuts to destinations using vector-based navigation.

We present a practical workflow describing how to use deep learning to develop continuous-risk models that can predict various adverse outcomes from structured electronic health records.