WP6 - Efficient & Scalable Platform for Analysis, Storage & Data Sharing
| Participating partner | Total Pm per organization |
|---|---|
| FORTH | 4 |
| PAGNI | - |
| NEUROCOM | 16 |
| UZH | - |
| PROMETRONICS | 13 |
| UA | 3 |
| BRUKER | - |
| HARVARD | - |
| UCLA | - |
Tasks 6.1 - 6.4
- Efficient temporal correlation analysis exploiting parallelism using high performance computing techniques, such as Multicore programming, and accelerators
- Efficient storage and retrieval of the subgraphs. A large graph database management system, based on state of the art technology, such as Neo4j will be deployed. The system will provide graph retrieval and similarity search operators.
- Implementation of the distributed machine learning algorithms for real-time prediction;
- Efficient querying of datasets according to the type of experiment (e.g., stimulus, layers, graph-theoretical properties of subnetworks, type of mouse)
Publications
D6.1 Software of the most important building blocks of the analysis, available in github for open access (Neurocom, M36,M48)
D6.2 TR with information about the architecture, methodology, techniques and technologies used along with a programmer’s guide for the use of libraries and utilities. Two updated versions throughout the project duration (Neurocom, M36, M48)
D5.3 TR with a description of the distributed ML algorithms (Forth, M36, M48)
D5.4 Guide for the data representation and querying the datasets (Neurocom, M36, M48)