Pedro J. Goncalves
@ppjgoncalves.bsky.social
Computational Neuroscience and Machine Learning. Group Leader at VIB-NERF (https://nerf.be/en#/) and Associate Professor at KU Leuven (https://www.kuleuven.be/english/kuleuven). Affiliated with VIB.AI (vib.ai/en).
More details at goncalveslab.sites.vib.be
More details at goncalveslab.sites.vib.be
Reposted by Pedro J. Goncalves
We apply our masked VAE approach to drosophila 🪰walking behavior, a macaque 🐒reach task & a synthetic dataset with access to the ground truth.
We propose calibration checks to evaluate the models’ uncertainty estimates, to avoid making confidently wrong predictions.
Check out the paper for more 🙂
We propose calibration checks to evaluate the models’ uncertainty estimates, to avoid making confidently wrong predictions.
Check out the paper for more 🙂
April 17, 2025 at 8:50 PM
We apply our masked VAE approach to drosophila 🪰walking behavior, a macaque 🐒reach task & a synthetic dataset with access to the ground truth.
We propose calibration checks to evaluate the models’ uncertainty estimates, to avoid making confidently wrong predictions.
Check out the paper for more 🙂
We propose calibration checks to evaluate the models’ uncertainty estimates, to avoid making confidently wrong predictions.
Check out the paper for more 🙂