A machine-learning algorithm fully describes how the cells function, and could help us simulate medical research more accurately.
Background: Virtually all AI systems are black boxes—algorithms that are impossible for us to examine. That’s fine for, say, tech firms doing image recognition, but biologists would like to understand what algorithms are doing, or it’s hard to know whether to trust them.
The news: IEEE Spectrum reports that researchers mapped all the functions of brewer’s yeast—a well-studied single-cell organism—to a neural network. That lets them understand how the AI describes biological behavior, making it a reliable research tool.
Why it matters: The algorithm has already given researchers new insight into the cell biology of yeast. Applied to human cells, it could spur advances by allowing researchers to simulate personalized treatments and discover new drugs.
But: Going from yeast to human cells will be tough. And the same problem that bugs computer scientists—a need for data—will frustrate medical researchers trying to hone complex human models. Of course, one day we might be able to just design genomes on computer screens.
Yann LeCun has a bold new vision for the future of AI
One of the godfathers of deep learning pulls together old ideas to sketch out a fresh path for AI, but raises as many questions as he answers.
Inside a radical new project to democratize AI
A group of over 1,000 AI researchers has created a multilingual large language model bigger than GPT-3—and they’re giving it out for free.
DeepMind has predicted the structure of almost every protein known to science
And it’s giving the data away for free, which could spur new scientific discoveries.
Sony’s racing AI destroyed its human competitors by being nice (and fast)
What Gran Turismo Sophy learned on the racetrack could help shape the future of machines that can work alongside humans, or join us on the roads.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.