3 papers
stat.ML2019
ODEVAE: Deep generative second order ODEs with Bayesian neural networks
Çağatay Yıldız, Markus Heinonen, Harri Lähdesmäki
We present Ordinary Differential Equation Variational Auto-Encoder (ODEVAE), a latent second order ODE model for high-dimensional sequential data. Leveraging the advances in de…
stat.ML2019
Learning spectrograms with convolutional spectral kernels
Zheyang Shen, Markus Heinonen, Samuel Kaski
We introduce the convolutional spectral kernel (CSK), a novel family of non-stationary, nonparametric covariance kernels for Gaussian process (GP) models, derived from the convolut…
cs.LG2018
Neural Non-Stationary Spectral Kernel
Sami Remes, Markus Heinonen, Samuel Kaski
Standard kernels such as Matérn or RBF kernels only encode simple monotonic dependencies within the input space. Spectral mixture kernels have been proposed as general-purpose, fle…