2 papers
cs.LG2018
Deep learning with differential Gaussian process flows
Pashupati Hegde, Markus Heinonen, Harri Lähdesmäki +1
We propose a novel deep learning paradigm of differential flows that learn a stochastic differential equation transformations of inputs prior to a standard classification or regres…
stat.ML2018
Variational zero-inflated Gaussian processes with sparse kernels
Pashupati Hegde, Markus Heinonen, Samuel Kaski
Zero-inflated datasets, which have an excess of zero outputs, are commonly encountered in problems such as climate or rare event modelling. Conventional machine learning approaches…