CORDIS

The SpaRTaN FP7 Marie Curie Initial Training Network trained a new generation of interdisciplinary researchers in sparse representations and compressed sensing, contributing to Europe’s leading role in scientific innovation.
By bringing together leading academic and industry groups with expertise in sparse representations, compressed sensing, machine learning and optimisation, and with an interest in applications such as hyperspectral imaging, audio signal processing and video analytics, this project created an interdisciplinary, trans-national and inter-sectorial training network to enhance mobility and training of researchers in this area.
Our research aim was to investigate new methods for sparse representations and compressed sensing, and to apply these new methods in key application areas. To achieve this, we had the following research objectives:
- To investigate new methods for sparse representations, including analysis sparsity, structural information, and dictionary learning;
- To use the developed methods for the analysis of a range of signals, such as:
- magnetic resonance imaging (MRI);
- hyperspectral imaging;
- audio and music signals;
- video sequences;
- To apply these methods to real-world problems, in particular through working with the private sector;
- To share research advances in theory and applications across the network;
- To disseminate the results of this research to a wide range of audiences.
SpaRTaN recruited 8 university-based ESRs and 2 SME-based ERs across 5 countries. The network has trained its Fellows in transferable skills, research software development and scientific topics.

Researcher Training
SpaRTaN held researcher development training in September 2015 and April 2016 to introduce ESRs to the challenges of crossing cultures, how to manage themselves and their supervisors, how to present their research and themselves, applying ethics to their research, their professional development. Software Carpentry courses were run to introduce researchers to the software tools to help them do better research. With a focus on reproducibility and reusable code, the skills are designed to be useful in both academia or industry.
In April 2016 the project teamed up with the MacSeNet ITN to host a Spring School offering lectures and tutorials covering the theory of sparse representations, compressed sensing and related topics, alongside applications of these methods in areas such as image processing, audio signal processing, and signal processing on graphs. The Spring School was open to researchers outside the network for free. This increased the number of attendees and the networking opportunities. All the Spring School course materials can be found on our website.
In November 2016 we ran a 3 day training event looking at collaborative research, reproducibility and science communication. We followed this with a sandpit event with teams made up of Fellows and academics from across the partners. Through this the researchers were able to put into practice the tools they had learnt in their previous training and start building collaborations within the network.
In Edinburgh we took advantage of the science festival in April 2017 to run a training week devoted to entrepreneurship and communication. We covered how to pitch ideas to funders and the public as well as working with the media. The researchers took these skills into the field on the last day, engaging with the public in Edinburgh park while wearing sandwich boards encouraging people to ask them about their research.
In June 2017 we hosted SPARS2017, this established workshop was a good venue for our researchers to present their work to the community and for us to host our second summer school. The summer school offered a range of tutorials, a poster session and a panel discussion.
Our last event was a workshop hosted in Paris in March 2018. This was preceded by 2 days of training for the Fellows including interview practice and next steps after your fellowship.
Additionally the Fellows have taken part in secondments across the network, many of them to SMEs. This has allowed them to experience the research industry and consider the impact their work can have in the real world.
Through these events we have encourage our Fellows to develop into “T shaped People” capable of adapting in a fast-moving research field.

Scientific Results
Since they started our Fellows have developed:
ER1-Several methods for audio source separation using deep and convolutional neural networks.
ER2-A fast method for kernel dictionary learning using sparsity constraints for increased speed in automatic music transcription.
ER3-A novel method for fast quantitative brain MRI with statistical modelling in multichannel coils.
ER4-A solution to complex inverse problems, through conversion of the signal to a novel domain.
ER5-An evaluation of deep neural network pruning methods and theoretical analysis of convolutional neural network performance.
ER6-A state of the art image denoising method using large, class-specific, image databases (e.g from the internet).
ER7-An exceptionally fast and robust method for hyper spectral image denoising, achieving state of the art results without hand-tuned parameters and two hyperspectral compression strategies.
ER8-A convergence acceleration technique for generic optimisation problems.
ER1-An algorithm which allows a 50% reduction in the x-ray radiation used to image breast cancers helping women all over the world.
ER2-A patentable technique for constructing 3D point clouds from multiple images which has been licenced to an industrial partner.
These scientific advances have been published in 32 peer-reviewed papers and 7 technical reports which can be found on our website www.spartan-itn.eu

Lessons Learnt
During this ITN many lessons have been learnt and a list is being compiled for others. These include:
Allow sufficient time for recruitment – it takes longer than you expect.
It is difficult to encourage experienced researchers to move countries for a short term contract.
Recruiters and organisers need to be aware of visa needs for recruiting and arranging events.
Allocate time to help ESRs/ERs to understand what they need to do as part of the network.
Identify good local trainers in each partner institution to help build training programmes.
Include visits to local teams during events, helping researchers to share their work with the network.
Combine events for economies but be sure to include time for people to digest what they have learnt.
Researcher Development Training works across fields and a mixed cohort is good for discussions.
Organise a network outreach event early on to show researchers they can do it and it is fun.
Get the Fellows involved in running the network and planning training, it makes it more relevant and is good experience.
Internet is important – always check that the WiFi in your venue is ready for the size of your group.

www-spartan-itn.eu