Machine Learning

Engineering molecular interactions with machine learning

By using deep learning-generated ‘fingerprints’ to characterize millions of protein fragments, EPFL researchers have computationally designed novel protein binders that attach seamlessly to key targets, including the SARS-CoV-2 spike protein.

A new form of human-computer interaction

Researchers from ETH Zurich created a new open-source platform and programming language called LMQL. This programming language makes it easier, cheaper, and safer to interact with large language models like ChatGPT.

Cryo-imaging lifts the lid on fuel cell catalyst layers

Thanks to a novel combination of cryogenic transmission electron tomography and deep learning, EPFL researchers have provided a first look at the nanostructure of platinum catalyst layers, revealing how they could be optimized for fuel cell efficiency.

Artificial intelligence is not a pandemic

There are concerns that ChatGPT could undermine the educational system, and growing demands for rules governing its use. Gerd Kortemeyer argues that anything but the most common sense regulations could end up being counterproductive.

Detecting stress in the office from how people type and click

Researchers at ETH Zurich have developed a model that detects workplace stress just by how people type and move their computer mouse. This might enable employees to prevent chronic stress early on.

New AI model transforms research on metal-organic frameworks

Researchers at EPFL and KAIST have developed a new AI model that significantly improves the understanding of metal-organic frameworks (MOFs), promising materials for hydrogen storage and other applications.

4 5 6

7

8 9 10 11...

Page 7 of 16