Computer Science
Deep learning: a framework for image analysis in life sciences
Research
EPFL
Deep learning models are becoming increasingly common in bioimage analysis. Yet a lack of standardization and the use of these algorithms by non-experts are potential sources of bias. Scientists from EPFL and the European Bioinformatics Institute (EMBL-EBI) offer practical tips and guidance in a paper recently published in the journal IEEE.
When it comes to forecasts, politics fails more often than science
Politics
ETH Zurich
Politicians and the media struggle with predictions. This is more a problem resulting from a poor understanding of uncertainties than from the reliability of models, argues Reto Knutti.
How human and artificial intelligence can augment one another
Research
ETH Zurich
Mennatallah El-Assady develops explainable AI programs that explain their own workings – and let users provide input. This can help analysts take a deep dive into political debate.  
Pass me the pastries, please
Research
EPFL
A new global study by researchers from EPFL, the University of Fribourg, and Microsoft Research has found there was an overall surge in high calorie foods such as pastries, bread and pies during the first wave of the COVID-19 pandemic, with potential implications for public health.
ETH graduates reinvent the user manual
TechTransfer
ETH Zurich
No sooner had David Shapira and Kordian Caplazi finished their studies than they set about creating a start-up. Rimon develops virtual user manuals for industrial companies, enabling users to quickly and intuitively learn how to operate complex machines with the aid of AR glasses.
Predicting complex dynamics from data
Research
ETH Zurich
Researchers at ETH Zurich have developed a new algorithm that allows them to model the dynamics of physical systems from observations. In the future it could be applied to the onset of turbulence and tipping points in climate.
Page 11 of 19