Projects per year
Abstract
We introduce the convolutional spectral kernel (CSK), a novel family of non-stationary, nonparametric covariance kernels for Gaussian process (GP) models, derived from the convolution between two imaginary radial basis functions. We present a principled framework to interpret CSK, as well as other deep probabilistic models, using approximated Fourier transform, yielding a concise representation of input-frequency spectrogram. Observing through the lens of the spectrogram, we provide insight on the interpretability of deep models. We then infer the functional hyperparameters using scalable variational and MCMC methods. On small- and medium-sized spatiotemporal datasets, we demonstrate improved generalization of GP models when equipped with CSK, and their capability to extract non-stationary periodic patterns.
Original language | English |
---|---|
Title of host publication | The 23rd International Conference on Artificial Intelligence and Statistics |
Editors | S Chiappa, R Calandra |
Pages | 3826-3836 |
Number of pages | 10 |
Publication status | Published - 2020 |
MoE publication type | A4 Article in a conference publication |
Event | International Conference on Artificial Intelligence and Statistics - Palermo, Italy Duration: 3 Jun 2020 → 5 Jun 2020 Conference number: 23 |
Publication series
Name | Proceedings of Machine Learning Research |
---|---|
Publisher | PMLR |
Volume | 108 |
ISSN (Print) | 2640-3498 |
Conference
Conference | International Conference on Artificial Intelligence and Statistics |
---|---|
Abbreviated title | AISTATS |
Country | Italy |
City | Palermo |
Period | 03/06/2020 → 05/06/2020 |
Fingerprint Dive into the research topics of 'Learning spectrograms with convolutional spectral kernels'. Together they form a unique fingerprint.
Projects
-
FCAI: Finnish Center for Artificial Intelligence (FCAI)
01/01/2019 → 31/12/2022
Project: Academy of Finland: Other research funding
-
Interactive machine learning from multiple biodata sources
01/01/2016 → 31/08/2021
Project: Academy of Finland: Other research funding