CEST research acknowledged at Physics Days
CEST masters student Manuel Kuchelmeister was awarded one of the two best poster prizes for his presentation "Multi-fidelity machine learning to accelerate materials research" at Physics Days 2022, organized virtually by Aalto University.
Bayesian optimization (BO) is a sample-efficient method for the exploration of large search spaces. In this work, BO is used to find stable configurations on material energy landscapes. Finding such structures is a challenge, due to high-dimensional search spaces and costly quantum mechanical calculations. Kuchelmeister approached this by constructing a multi-fidelity machine learning model. By using a transfer learning approach, it was possible to use less accurate but inexpensive calculations, to accelerate the exploration phases of BO.
The approach reduced the computational cost of a conformer search problem by 70%, serving as a first benchmark for the great potential that multi-fidelity learning can have to accelerate expensive structure-search problems.
Read more news
Five things everyone should know about creativity
Creativity is not the preserve of artists or a rare innate talent but a human capacity we all share – and one that can be measured, developed, and led for. The two-year Creative Leap project explored how creativity shows up in everyday life and work and how it connects to companies’ financial results. Here are five key takeaways.
Arjen valintoja: Frank Martela, onko onnellisuus vakava asia?
Apulaisprofessori ja filosofi tutkii ihmisen hyvinvointia ja motivaatiota.
Hope is not just awaited – it is studied, questioned and created at Aalto University
According to the dictionary, hope is the feeling that something desirable is likely to happen. A writer set out to search for hope on the university campus – and encountered fulfilled wishes, critical hope studies, and the kind of hope you have to create yourself.