Probabilistic Numeric Convolutional Neural Networks

10/21/2020
by   Marc Finzi, et al.
0

Continuous input signals like images and time series that are irregularly sampled or have missing values are challenging for existing deep learning methods. Coherently defined feature representations must depend on the values in unobserved regions of the input. Drawing from the work in probabilistic numerics, we propose Probabilistic Numeric Convolutional Neural Networks which represent features as Gaussian processes (GPs), providing a probabilistic description of discretization error. We then define a convolutional layer as the evolution of a PDE defined on this GP, followed by a nonlinearity. This approach also naturally admits steerable equivariant convolutions under e.g. the rotation group. In experiments we show that our approach yields a 3× reduction of error from the previous state of the art on the SuperPixel-MNIST dataset and competitive performance on the medical time series dataset PhysioNet2012.

READ FULL TEXT
research
08/06/2023

Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series

Irregularly sampled multivariate time series are ubiquitous in several a...
research
08/17/2020

Learning from Irregularly-Sampled Time Series: A Missing Data Perspective

Irregularly-sampled time series occur in many domains including healthca...
research
09/17/2022

Interrelation of equivariant Gaussian processes and convolutional neural networks

Currently there exists rather promising new trend in machine leaning (ML...
research
01/10/2020

Temporally Folded Convolutional Neural Networks for Sequence Forecasting

In this work we propose a novel approach to utilize convolutional neural...
research
09/17/2020

Automatic Forecasting using Gaussian Processes

Automatic forecasting is the task of receiving a time series and returni...
research
04/17/2021

Recursive input and state estimation: A general framework for learning from time series with missing data

Time series with missing data are signals encountered in important setti...
research
05/30/2020

Learning Efficient Representations of Mouse Movements to Predict User Attention

Tracking mouse cursor movements can be used to predict user attention on...

Please sign up or login with your details

Forgot password? Click here to reset