Project SGL Thresh (CERCO - IRIT Samova team)
Surrogate Gradient Learning of Thresholds
The objective is to set optimal thresholds for a multi-label classification problem
Project REAM (IRIT ADRIA and MELODI teams)
Explicit Reasoning and Learning in Medical Imaging.
Project ANITI - DAML (Université Fédérale de Toulouse MIP)
Combining data assimilation and machine learning techniques for learning under physical constraints..
Project Hearvolution (IRIT - Team REVA, AMIS Laboratory UT3)
Identification of positive selection signatures in genes involved in auditory processes at the interspecific scale in human and non-human primates.
Toulouse School of Economics
Parallélisation sur GPU des codes pour l'étude d'un modèle de demande à choix discret pour l'économie de l'alimentation.
Project Nurisens (IRIT - Team SIG, INSERM I2MC, Innopsys, Keleo Solutions, Flutilliant companies)
Development of data analysis and correlation algorithms for urinary autotests for nutritional monitoring and sports activity.
Project DIAMEN (IRIT - Team SIG, CHU Toulouse, ORME Company)
Development of a diagnostic aid tool in cardiac scans of nuclear medicine departments.
Project aireps (IRIT - Team MELODI, CERCO Laboratory)
Analysis of semantic representations, comparison of human and AI representations
Project dfo4rl (IRIT - Team APO, Lehigh Université (USA))
Development of no derivative optimization algorithms for reinforcement learning.
Project Flux Doppler (IRIT - Team MINDS, Université de Tours CHU)
Measurement of blood flow from Doppler signals by ultrafast acquisition
Project Néocampus (IRIT)
Training of neural networks for smart sensors. First applications: attendance measurements, detection of Asian hornets at the apiary, ...
COOSINET Project (IRIT Team SC - CNES (Toulouse), Thales (Cannes))
Compression Onboard Of Satellite Images using neural NETworks
Text mining project on scientific literature (IRIT IRIS team - INIST)
The project aims to apply text mining techniques (in particular word embeddings) on large corpuses of scientific literature (in the order of 20 million texts on ISTEX, for example).
SIERA team (IRIT)
Detection of network intrusion & weak signals
Project LINTO (LINAGORA company - IRIT (SAMoVA and MELODI teams) - LAAS - Zelros company - LIX (Ecole Polytechnique - Saclay))
Conversational assistant working in a professional environment
Project ANR COST (IRIT - CLLE (Toulouse), LIG (Grenoble), LIP6 (Paris))
Modelling Complex Tasks in Information Research
Project Image CLEF 2019 (IRIT - Univ. Toulouse 3)
Deep learning for medical data and participation in the CLEF challenge
Tools for Dataset Description
Project ClustEdu (IRIT)
Discourse analysis via clustering methods
SEPIA Team activity (IRIT)
Scalability of Machine Learning with TensorFlow.
Project LF2A (IRIT/CIMI)
Logical Frameworks for Abstract Argumentation.
Project DeepEmbryo (IRIT)
Deep Learning on 3D dataset from live embryo.
Project Deforestation (IRIT - Univ. Madagascar) hosting :
Applying machine learning algorithms (CNN) on satellite images for annotation and change detection.
15 january 2018
A GPU computing cluster (7 Dell T630 servers with 28 Nvidia Geforce GTX 1080 TI cards) is available on the Osirim platform. The deep learning frameworks Tensorflow, Pytorch , Theano and Keras can be used on this cluster via Slurm.
Victoria (UPS, INP / IRIT) project hosting
H2020 Project - SEC (Video Analysis for Investigation of Criminal and Terrorist Activities) for the dissemination of large reference corpuses (several Teras) between the different teams in Europe.
10 november 2017
networkx and rpy2 packages are available on the platform for Python versions 2.7.13 and 3.5.2
22 august 2017
Scikit-learn and ngram packages are available on the platform for Python version 2.7.13.
20 july 2017
TreeTagger and TreeTaggerWrapper for Python are available on the platform.
"The TreeTagger is a tool for annotating text with part-of-speech and lemma information. It has been successfully used to tag German, English, French, Italian, Dutch, Spanish, Bulgarian, Russian, Portuguese, Galician, Chinese, Swahili, Slovak, Slovenian, Latin, Estonian, Polish, Romanian, Czech, Coptic and old French texts and is adaptable to other languages if a lexicon and a manually tagged training corpus are available." (http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/)
30 march 2017
Depression (IRIT, LIMSI) project hosting
The aim of the project is to detect depressed people via their posts on social networks by first using CLEF's e-risk collection and other collections.
13 march 2017
Indri and Pyndri are available on the plateform.
"Indri is a new search engine from the Lemur project; a cooperative effort between the University of Massachusetts and Carnegie Mellon University to build language modeling information retrieval tools" (https://www.lemurproject.org/indri/)
"pyndri is a Python interface to the Indri search engine" (https://github.com/cvangysel/pyndri)
27 february 2017
A new version of SLURM is deployed on Osirim. On this occasion, the calculation cluster SLURM has been completely redesigned, as well as the access modalities.
3 January 2017
The new corpus MS-Marco (http://www.msmarco.org/) is avalaible on OSIRIM.
MS-Marco (Microsoft MAchine Reading COmprehension Dataset) is a Reading Comprehension Dataset for the Artificial Intelligence research community .