8 citations · 10 across the 3 of their papers we have counts for
4 papers
Fixing Overconfidence in Dynamic Neural Networks
Lassi Meronen, Martin Trapp, Andrea Pilzer +2
Dynamic neural networks are a recent technique that promises a remedy for the increasing size of modern deep learning models by dynamically adapting their computational cost to the…
Periodic Activation Functions Induce Stationarity
Lassi Meronen, Martin Trapp, Arno Solin
Neural network models are known to reinforce hidden data biases, making them unreliable and difficult to interpret. We seek to build models that `know what they do not know' by int…
Stationary Activations for Uncertainty Calibration in Deep Learning
Lassi Meronen, Christabella Irwanto, Arno Solin
We introduce a new family of non-linear neural network activation functions that mimic the properties induced by the widely-used Matérn family of kernels in Gaussian process (GP) m…
Movement Tracking by Optical Flow Assisted Inertial Navigation
Lassi Meronen, William J. Wilkinson, Arno Solin
Robust and accurate six degree-of-freedom tracking on portable devices remains a challenging problem, especially on small hand-held devices such as smartphones. For improved robust…