Orateur
Masahiko Saito
(International Center for Elementary Particle Physics, University of Tokyo)
Description
To efficiently solve a big problem by deep learning, it is sometimes useful to decompose it into smaller blocks, enabling us to introduce our knowledge into the model by utilizing an appropriate loss function for each block.
A simple model decomposition, however, causes a performance decrease due to bottlenecks of transferred information induced by the loss definition.
We proposed a method to mitigate such a bottleneck by using hidden features instead of outputs that are defined for the loss function, and experimentally demonstrated the usefulness using a particle physics dataset.
We also demonstrated the adaptive tuning of loss coefficients of each task based on techniques in multi-task learning.
Auteur principal
Masahiko Saito
(International Center for Elementary Particle Physics, University of Tokyo)
Co-auteurs
Dr
Tomoe Kishimoto
Dr
Masahiro Morinaga
Dr
Sanmay Ganguly
Prof.
Junichi Tanaka
