Deep learning and Bayesian inference for medical imaging

Informazioni relative al progetto

DeeBMED

ID dell’accordo di sovvenzione: 702666

DOI 10.3030/702666

Progetto chiuso

Data della firma CE 17 Febbraio 2016

Data di avvio 1 Ottobre 2016

Data di completamento 30 Settembre 2018

Finanziato da

• EXCELLENT SCIENCE - Marie Skłodowska-Curie Actions

Costo totale € 177 598,80

Contributo UE € 177 598,80

Coordinato da

UNIVERSITEIT VAN AMSTERDAM
Netherlands

Pubblicazioni

Conference proceedings (11)

VAE with a VampPrior

Autori: Jakub Tomczak, Max Welling
Pubblicato in: Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics, Numero PMLR 84, 2018, Pagina/e 1214-1223
Editore: Journal of Machine Learning Research

Improving variational auto-encoders using householder flow

Autori: Jakub M Tomczak, Max Welling
Pubblicato in: Bayesian Deep Learning Workshop @ NIPS 2016, 2016, Pagina/e 8
Editore: Bayesian Deep Learning Workshop @ NIPS 2016

Improving Variational Auto-Encoders using convex combination linear Inverse Autoregressive Flow

Autori: Jakub M. Tomczak, M Welling
Pubblicato in: Benelearn 2017: Proceedings of the Twenty-Sixth Benelux Conference on Machine Learning, 2017, Pagina/e 162-164
Editore: TU/e

A deep multiple instance model to predict prostate cancer metastasis from nuclear morphology

Autori: Nathan Ing, Jakub M Tomczak, Eric Miller, Isla P Garraway, Max Welling, Beatrice S Knudsen, Arkadiusz Gertych
Pubblicato in: Medical Imaging with Deep Learning, 2018
Editore: OpenReview

Deep Learning with Order-invariant Operator for Multi-instance Histopathology Classification

Autori: Jakub Tomczak, Maximilian Ilse and Max Welling
Pubblicato in: MEDICAL IMAGING MEETS NIPS 2017, 2017
Editore: arXiv

Sylvester Normalizing Flows for Variational Inference

Autori: Rianne van den Berg, Leonard Hasenclever, Jakub M. Tomczak, Max Welling
Pubblicato in: Uncertainty in Artificial Intelligence Proceedings of the Thirty-Fourth Conference (2018), 2018
Editore: UAI 2018

Attention-based Deep Multiple Instance Learning

Autori: Maximilian Ilse, Jakub Tomczak, Max Welling
Pubblicato in: Volume 80: International Conference on Machine Learning, 10-15 July 2018, Stockholmsmässan, Stockholm Sweden, Numero PMLR 80, 2018, Pagina/e 2127-2136
Editore: PMLR

Hierarchical VampPrior Variational Fair Auto-Encoder

Autori: Philip Botros and Jakub Tomczak
Pubblicato in: Theoretical Foundations and Applications of Deep Generative Models @ ICML 2018, 2018
Editore: Theoretical Foundations and Applications of Deep Generative Models @ ICML 2018

Variational Inference with Orthogonal Normalizing Flows

Autori: Leonard Hasenclever, Jakub Tomczak, Rianne van den Berg and Max Welling
Pubblicato in: Bayesian Deep Learning @ NIPS 2017, 2017
Editore: Bayesian Deep Learning @ NIPS 2017

Histopathological classification of precursor lesions of esophageal adenocarcinoma: A Deep Multiple Instance Learning Approach

Autori: Jakub M Tomczak, Maximilian Ilse, Max Welling, Marnix Jansen, Helen G Coleman, Marit Lucas, Kikki de Laat, Martijn de Bruin, Henk Marquering, Myrtle J van der Wel, Onno J de Boer, C Dilara Savci Heijink, Sybren L Meijer
Pubblicato in: Medical Imaging with Deep Learning, 2018
Editore: OpenReview

Hyperspherical Variational Auto-Encoders

Autori: Tim R. Davidson, Luca Falorsi, Nicola De Cao, Thomas Kipf, Jakub M. Tomczak
Pubblicato in: Uncertainty in Artificial Intelligence Proceedings of the Thirty-Fourth Conference (2018), 2018
Editore: UAI 2018