1 code implementation • 13 Feb 2023 • Lassi Meronen, Martin Trapp, Andrea Pilzer, Le Yang, Arno Solin
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 difficulty of the inputs.
2 code implementations • NeurIPS 2021 • Lassi Meronen, Martin Trapp, Arno Solin
Neural network models are known to reinforce hidden data biases, making them unreliable and difficult to interpret.
1 code implementation • NeurIPS 2020 • 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 Mat\'ern family of kernels in Gaussian process (GP) models.
no code implementations • 24 Jun 2020 • Lassi Meronen, William J. Wilkinson, Arno Solin
We consider a visually dense approach, where the IMU data is fused with the dense optical flow field estimated from the camera data.