Understanding and improving machine learning model uncertainty estimates
Modern machine learning methods including deep learning have achieved great success in predictive accuracy for supervised learning tasks, but may still fall short in giving useful estimates of their predictive uncertainty.
With the advent of autonomous vehicles, LiDAR and cameras have become an indispensable combination of sensors.
We believe that we can put the power of eye tracking in everyone's palm by building eye tracking software that works on commodity hardware such as mobile phones and tablets, without the need for additional sensors or devices.
Steady-State Visual Evoked Potentials (SSVEPs) are neural oscillations from the parietal and occipital regions of the brain that are evoked from flickering visual stimuli.
Combining the local permutation scheme with the kernel tests leads to better calibration, but suffers in power.
In this paper, we propose a novel training methodology that consistently outperforms cross entropy on supervised learning tasks across different architectures and data augmentations.
#53 best model for Image Classification on ImageNet