Deep learning

By tapping into a decades-old mathematical principle, researchers are hoping that Kolmogorov-Arnold networks will facilitate scientific discovery.

Neural networks and other forms of machine learning ultimately learn by trial and error, one improvement at a time.

Three years ago, Google’s AlphaFold pulled off the biggest artificial intelligence breakthrough in science to date, accelerating molecular research and kindling deep questions about why we do science.

Google DeepMind’s AlphaFold3 and other deep learning algorithms can now predict the shapes of interacting complexes of protein, DNA, RNA and other molecules, better capturing cells’ biological landscapes.

By bringing together disparate approaches, machines can reach a new level of creative problem-solving.

A new result shows how much of the plane can be colored by points that are never exactly one unit apart.

A wave of research improves reinforcement learning algorithms by pre-training them as if they were human.

Diffusion models generate incredible images by learning to reverse the process that, among other things, causes ink to spread through water.

Making sure our machines understand the intent behind our instructions is an important problem that requires understanding intelligence itself.