DEDALE project deliverables
The page lists 13 deliverables related to the research project "DEDALE".
List of Deliverables
| title and desprition | type | last update |
|---|---|---|
Numerical toolbox and benchmarking platform.Development of a numerical toolbox and benchmark test set. The code will be Programme: H2020-EU.1.2.1. - Topic(s): FETOPEN-RIA-2014-2015 |
Demonstrators, pilots, prototypes | 2019-04-30 |
Optimizations for non-linear learning.Report on building upon proximal methods and problem splitting techniques to design highly-parallelizable sparse solvers (e.g. sparse/low-rank multivariate signal decompositions.) Programme: H2020-EU.1.2.1. - Topic(s): FETOPEN-RIA-2014-2015 |
Documents, reports | 2019-04-30 |
Dictionary learning for multivariate/multispectral data.Report on Dictionary Learning on multi-valued data. The case of multi-channel polarized data on the sphere will be considered. Programme: H2020-EU.1.2.1. - Topic(s): FETOPEN-RIA-2014-2015 |
Documents, reports | 2019-04-30 |
Super-resolution and interpolation of the Euclid PSFReport on applying dictionary learning on manifolds developed in DEDALE in combination with interpolation methods which are used extensively by the UCL group (e.g neural networks and Gaussian processes) to build a model for the Euclid PSF. Programme: H2020-EU.1.2.1. - Topic(s): FETOPEN-RIA-2014-2015 |
Documents, reports | 2019-04-30 |
Toolbox and benchmarking platform for large scale learning.Toolbox for parallel linear and non-linear sparsity based learning architectures. Programme: H2020-EU.1.2.1. - Topic(s): FETOPEN-RIA-2014-2015 |
Demonstrators, pilots, prototypes | 2019-04-30 |
Optimization for manifold-valued signal restoration.Report on optimization methods for signal restoration with manifold-valued representations: Programme: H2020-EU.1.2.1. - Topic(s): FETOPEN-RIA-2014-2015 |
Documents, reports | 2019-04-30 |
Non-linear learning on complex imaging data.Report on Non-linear learning on complex imaging data: learning representations for data lying on unknown low-dimensional manifolds. The use of deep learning architectures like stacked sparse autoencoders will be particularly studied in this task. Programme: H2020-EU.1.2.1. - Topic(s): FETOPEN-RIA-2014-2015 |
Documents, reports | 2019-04-30 |
Evaluation/validation of the mass mapping algorithmsReport on using dictionary methods for 2D and 3D mass mapping from weak lensing data. Programme: H2020-EU.1.2.1. - Topic(s): FETOPEN-RIA-2014-2015 |
Open Research Data Pilot | 2019-04-30 |
Linear inverse problems with sparsity constraints.Report on the development of dedicated solvers for the recovery of multivariate signals with adapted sparse priors, either in fixed representations from Task 2.1 or learnt representations from task 2.2. Programme: H2020-EU.1.2.1. - Topic(s): FETOPEN-RIA-2014-2015 |
Documents, reports | 2019-05-30 |
Large-scale learning schemes.Evaluation of cutting edge distributed processing platforms, such as GraphLab, Mahout and MLI, for benchmarking large-scale test sets for machine learning. Real time parallel processing considerations will be actively taken under account into this task. Programme: H2020-EU.1.2.1. - Topic(s): FETOPEN-RIA-2014-2015 |
Documents, reports | 2019-05-30 |
Adaptive transforms for manifold-valued data.Report on the development of adapted multiscale transforms. The final learned dictionary is restricted to a class of dictionaries generated from a structured dictionary such as shearlet. Existence of fast transform/reconstruction will be discussed. Programme: H2020-EU.1.2.1. - Topic(s): FETOPEN-RIA-2014-2015 |
Documents, reports | 2019-05-30 |
Learning-based photometric and spectroscopic redshift estimationReport on the development of a dictionary learning based method for spectroscopic and photometric Programme: H2020-EU.1.2.1. - Topic(s): FETOPEN-RIA-2014-2015 |
Documents, reports | 2019-05-30 |
Project Website & FactsheetRealization of web site, contains informations about the project (publications, technical notes, etc). Programme: H2020-EU.1.2.1. - Topic(s): FETOPEN-RIA-2014-2015 |
Websites, patent fillings, videos etc. | 2019-05-30 |