Jean-Luc Starck – CosmoStat

Benchmarking MRI Reconstruction Neural Networks on Large Public Datasets

Posted on March 6, 2020March 6, 2020 by Jean-Luc Starck

Deep learning is starting to offer promising results for reconstruction in Magnetic Resonance Imaging (MRI). A lot of networks are being developed, but the comparisons remain hard because the frameworks used are not the same among studies, the networks are not properly re-trained, and the datasets used are not the same among comparisons. The recent release of a public dataset, fastMRI, consisting of raw k-space data, encouraged us to write a consistent benchmark of several deep neural networks for MR image reconstruction. This paper shows the results obtained for this benchmark, allowing to compare the networks, and links the open source implementation of all these networks in Keras. The main finding of this benchmark is that it is beneficial to perform more iterations between the image and the measurement spaces compared to having a deeper per-space network.

Reference: Z. Ramzi, P. Ciuciu and J.-L. Starck. “Benchmarking MRI reconstruction neural networks on large public datasets”, Applied Sciences, 10, 1816, 2020. doi:10.3390/app10051816

The first Deep Learning reconstruction of dark matter maps from weak lensing observational data

Posted on January 14, 2020January 14, 2020 by Jean-Luc Starck

This is the first reconstruction of dark matter maps from weak lensing observational data using deep learning. We train a convolution neural network (CNN) with a Unet based architecture on over 3.6 x 10^5 simulated data realisations with non-Gaussian shape noise and with cosmological parameters varying over a broad prior distribution. Our DeepMass method is substantially more accurate than existing mass-mapping methods. With a validation set of 8000 simulated DES SV data realisations, compared to Wiener filtering with a fixed power spectrum, the DeepMass method improved the mean-square-error (MSE) by 11 per cent. With N-body simulated MICE mock data, we show that Wiener filtering with the optimal known power spectrum still gives a worse MSE than our generalised method with no input cosmological parameters; we show that the improvement is driven by the non-linear structures in the convergence. With higher galaxy density in future weak lensing data unveiling more non-linear scales, it is likely that deep learning will be a leading approach for mass mapping with Euclid and LSST.

Reference 1: N. Jeffrey, F. Lanusse, O. Lahav, J.-L. Starck, "Learning dark matter map reconstructions from DES SV weak lensing data", Monthly Notices of the Royal Astronomical Society, in press, 2019.

Machine Learning for Euclid Mass Mapping and Cosmological Parameter Estimation

Posted on November 18, 2019November 18, 2019 by Jean-Luc Starck

Deep Learning on the Sphere and Reconstruction of Dark Matter Mass Maps

Posted on October 3, 2019 by Jean-Luc Starck

GOLD : The Golden Cosmological Surveys Decade

Posted on July 6, 2019May 18, 2020 by Jean-Luc Starck

This 10-week programme on the Golden Cosmological Surveys Decade will be held at the new Institut Pascal, in Paris Orsay, from 1st April 2020 to 5th June 2020. The Institut Pascal provides offices, seminar rooms, common areas and supports long-term scientific programmes.

GOLD 2020 will include a summer school, three workshops (on Lensing, Galaxy Clustering, Theory and Interpretation of the Data).

In-between, an active training programme will be run. We plan to host around 40 people for the whole programme, plus around 30 scientists during the workshops.

Whether you are a PhD, a postdoc, a senior scientist and are interested in attending this programme, you can now apply. Deadline for applications: 1st October 2019.

WORKSHOP ON COMPUTATIONAL INTELLIGENCE IN REMOTE SENSING AND ASTROPHYSICS

Posted on March 29, 2019September 17, 2019 by Jean-Luc Starck

The workshop on Computational Intelligence in Remote Sensing and Astrophysics (CIRSA) aims at bringing together researchers from the environmental sciences, astrophysics and computer science communities in an effort to understand the potential and pitfalls of novel computational intelligence paradigms including machine learning and large-scale data processing.