Predicting the relationship between a molecules structure and its odor remains a difficult, decades-old task. This problem, termed quantitative structure-odor relationship (QSOR) modeling, is an important challenge in chemistry, impacting human nutrition, manufacture of synthetic fragrance, the environment, and sensory neuroscience. We propose the use of graph neural networks for Read more
by Antonie Louise Bierling ,Ilona Croy, Thomas Hummel, Gianaurelio Cuniberti and Alexander Croy A growing body of research aims at solving what is often referred to as the stimulus-percept problem in olfactory perception. Although computational efforts have made it possible to predict perceptual impressions from the physicochemical space of odors, studies with large psychophysical datasets from non-experts Read more
The L2 pilot study – CROWN – will be divided into two parts: In a first large-scale study, 1,200 participants will be asked to rate a total of 80 odor molecules in different dimensions and to complete questionnaires about their personality and experience with odors. In a second step, 60 Read more
The student newspaper “Psycho-Path” reports about Perceptronics in a general article about olfaction, olfactory disorders and why we need electronic noses. The full article can be read here on page 44.
The TU Dresden newspaper “Universitätsjournal” gives a detailed article about our project, its goals, and involved institutions and the international workshop. Read all details (in German) here on page 7.
In the German online blog by Heiko Weckbrodt, a new article informs about Perceptronics’ goals and approach as well as about the international workshop. Check it out here.
We are working on establishing a close collaboration between the work groups and are planning an international workshop gathering leading experts in the fields of (nano) sensorics, olfaction, perception and machine learning