Opendata, web and dolomites

PANAMA SIGNED

Probabilistic Automated Numerical Analysis in Machine learning and Artificial intelligence

Total Cost €

0

EC-Contrib. €

0

Partnership

0

Views

0

Project "PANAMA" data sheet

The following table provides information about the project.

Coordinator
EBERHARD KARLS UNIVERSITAET TUEBINGEN 

Organization address
address: GESCHWISTER-SCHOLL-PLATZ
city: TUEBINGEN
postcode: 72074
website: www.uni-tuebingen.de

contact info
title: n.a.
name: n.a.
surname: n.a.
function: n.a.
email: n.a.
telephone: n.a.
fax: n.a.

 Coordinator Country Germany [DE]
 Total cost 1˙450˙000 €
 EC max contribution 1˙450˙000 € (100%)
 Programme 1. H2020-EU.1.1. (EXCELLENT SCIENCE - European Research Council (ERC))
 Code Call ERC-2017-STG
 Funding Scheme ERC-STG
 Starting year 2018
 Duration (year-month-day) from 2018-03-01   to  2023-02-28

 Partnership

Take a look of project's partnership.

# participants  country  role  EC contrib. [€] 
1    EBERHARD KARLS UNIVERSITAET TUEBINGEN DE (TUEBINGEN) coordinator 1˙396˙663.00
2    MAX-PLANCK-GESELLSCHAFT ZUR FORDERUNG DER WISSENSCHAFTEN EV DE (MUENCHEN) participant 53˙336.00

Map

 Project objective

Numerical tasks - integration, linear algebra, optimization, the solution of differential equations - form the computational basis of machine intelligence. Currently, human designers pick methods for these tasks from toolboxes. The generic algorithms assembled in such collections tend to be inefficient on any specific task, and can be unsafe when used incorrectly on problems they were not designed for. Research in numerical methods thus carries carries the potential for groundbreaking advancements in the performance and quality of AI.

Project PANAMA will develop a framework within which numerical methods can be constructed in an increasingly automated fashion; and within which numerical methods can assess their own suitability, and adapt both model and computations to the task, at runtime. The key tenet is that numerical methods, since they perform tractable computations to estimate a latent quantity, can themselves be interpreted explicitly as active inference agents; thus concepts from machine learning can be translated to the numerical domain. Groundwork for this paradigm - probabilistic numerics - has recently been developed into a rigorous mathematical framework by the PI and others. The proposed research will simultaneously deliver new general theory for the computations of learning machines, and concrete new algorithms for core areas of machine learning. In doing so, Project PANAMA will improve the efficiency and safety of artificial intelligence, addressing scientific, technological and societal challenges affecting Europeans today.

 Publications

year authors and title journal last update
List of publications.
2019 Alexandra Gessner, Javier Gonzalez, Maren Mahsereci
Active Multi-Information Source Bayesian Quadrature
published pages: , ISSN: , DOI:
Conference on Uncertainty in Artificial Intelligence (UAI) 35 2019-12-17
2019 Filip Tronarp, Hans Kersting, Simo Särkkä, Philipp Hennig
Probabilistic solutions to ordinary differential equations as nonlinear Bayesian filtering: a new perspective
published pages: 1297-1315, ISSN: 0960-3174, DOI: 10.1007/s11222-019-09900-1
Statistics and Computing 29/6 2019-12-17
2019 Alexandra Gessner, Javier Gonzalez, Maren Mahsereci
Active Multi-Information Source Bayesian Quadrature
published pages: , ISSN: , DOI:
Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI) 2019-12-17
2018 Takafumi Kajihara, Motonobu Kanagawa, Keisuke Yamazaki, and Kenji Fukumizu
Kernel Recursive ABC: Point Estimation with Intractable Likelihood
published pages: 2400-2409, ISSN: , DOI:
Proceedings of the International Conference on Machine Learning 35 2019-12-17
2018 Lukas Balles, Philipp Hennig
Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients
published pages: 404--413, ISSN: , DOI:
Proceedings of the 35th International Conference on Machine Learning (ICML) 35 2019-12-17
2019 Toni Karvonen, Motonobu Kanagawa, Simo Särkkä
On the positivity and magnitudes of Bayesian quadrature weights
published pages: 1317-1333, ISSN: 0960-3174, DOI: 10.1007/s11222-019-09901-0
Statistics and Computing 29/6 2019-12-17
2019 Motonobu Kanagawa, Philipp Hennig
Convergence Guarantees for Adaptive Bayesian Quadrature Methods
published pages: 6234--6245, ISSN: , DOI:
Advances in Neural Information Processing Systems (NeurIPS) 32 2019-12-17
2019 Motonobu Kanagawa, Bharath K. Sriperumbudur, Kenji Fukumizu
Convergence Analysis of Deterministic Kernel-Based Quadrature Rules in Misspecified Settings
published pages: 1-40, ISSN: 1615-3375, DOI: 10.1007/s10208-018-09407-7
Foundations of Computational Mathematics 2019-12-17
2019 Frederik Kunstner, Philipp Hennig, Lukas Balles
Limitations of the empirical Fisher approximation for natural gradient descent
published pages: 4158--4169, ISSN: , DOI:
Advances in Neural Information Processing Systems (NeurIPS) 32 2019-12-17
2019 Filip de Roos, Philipp Hennig
Active Probabilistic Inference on Matrices for Pre-Conditioning in Stochastic Optimization
published pages: 1448--1457, ISSN: , DOI:
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS) 22 2019-12-17
2019 Georgios Arvanitidis, Soren Hauberg, Philipp Hennig, Michael Schober
Fast and Robust Shortest Paths on Manifolds Learned from Data
published pages: 1506--1515, ISSN: , DOI:
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS) 22 2019-12-17
2019 Schneider, Frank; Balles, Lukas; Hennig, Philipp
DeepOBS: A Deep Learning Optimizer Benchmark Suite
published pages: , ISSN: , DOI:
International Conference on Learning Representations (ICLR) 7 2019-12-17
2019 Simon Bartels, Jon Cockayne, Ilse C. F. Ipsen, Philipp Hennig
Probabilistic linear solvers: a unifyingview
published pages: 1249-1263, ISSN: 0960-3174, DOI: 10.1007/s11222-019-09897-7
Statistics and Computing 29/6 2019-12-17

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "PANAMA" project.

For instance: the website url (it has not provided by EU-opendata yet), the logo, a more detailed description of the project (in plain text as a rtf file or a word file), some pictures (as picture files, not embedded into any word file), twitter account, linkedin page, etc.

Send me an  email (fabio@fabiodisconzi.com) and I put them in your project's page as son as possible.

Thanks. And then put a link of this page into your project's website.

The information about "PANAMA" are provided by the European Opendata Portal: CORDIS opendata.

More projects from the same programme (H2020-EU.1.1.)

E-DIRECT (2020)

Evolution of Direct Reciprocity in Complex Environments

Read More  

DOUBLE-TROUBLE (2020)

Replaying the ‘genome duplication’ tape of life: the importance of polyploidy for adaptation in a changing environment

Read More  

ARCTIC (2020)

Air Transport as Information and Computation

Read More