Neuro-symbolic Neurodegenerative Disease Modeling as Probabilistic Programmed Deep Kernels

09/16/2020
by   Alexander Lavin, et al.
0

We present a probabilistic programmed deep kernel learning approach to personalized, predictive modeling of neurodegenerative diseases. Our analysis considers a spectrum of neural and symbolic machine learning approaches, which we assess for predictive performance and important medical AI properties such as interpretability, uncertainty reasoning, data-efficiency, and leveraging domain knowledge. Our Bayesian approach combines the flexibility of Gaussian processes with the structural power of neural networks to model biomarker progressions, without needing clinical labels for training. We run evaluations on the problem of Alzheimer's disease prediction, yielding results surpassing deep learning and with the practical advantages of Bayesian non-parametrics and probabilistic programming.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/31/2021

Probabilistic Deep Learning with Probabilistic Neural Networks and Deep Probabilistic Models

Probabilistic deep learning is deep learning that accounts for uncertain...
research
02/19/2023

Guided Deep Kernel Learning

Combining Gaussian processes with the expressive power of deep neural ne...
research
06/02/2017

Multiple Kernel Learning and Automatic Subspace Relevance Determination for High-dimensional Neuroimaging Data

Alzheimer's disease is a major cause of dementia. Its diagnosis requires...
research
08/27/2019

Multi-Task Gaussian Processes and Dilated Convolutional Networks for Reconstruction of Reproductive Hormonal Dynamics

We present an end-to-end statistical framework for personalized, accurat...
research
04/25/2021

Deep Probabilistic Graphical Modeling

Probabilistic graphical modeling (PGM) provides a framework for formulat...
research
02/20/2020

Bayesian Deep Learning and a Probabilistic Perspective of Generalization

The key distinguishing property of a Bayesian approach is marginalizatio...
research
06/05/2018

Probabilistic Deep Learning using Random Sum-Product Networks

Probabilistic deep learning currently receives an increased interest, as...

Please sign up or login with your details

Forgot password? Click here to reset