The software Antidote (www.antidote.info) is capable of correcting English and French corpuses. It detects thousands of types of errors. We want to add new types of correction using modules based on deep learning. The detection of missing words is a type of correction that we want to address in this internship. Here is an example of a sentence where Antidote displays a break (analysis problem), but which a deep learning model could correct:
If the project performs well, the intern will be able to try an integration of his model in our Antidote software.
The first objective is to use ML to reduce the modeling error in predicting the end-of-growth of a batch, reducing the emission of CO2 and water consumption of synthesized products. The second objective is to formulate the algorithms to facilitate its integration into our analytics solution. The third objective is to validate shared learning when applied for 1) forecasting other events and 2) forecasting the same events using similar but different datasets from different users.
Deep learning technology is a great tool to learn complex patterns and make prediction based on this learning. In order to get the most accurate predictions, one needs to train those neural networks on vast amount of labelled data. Labelling data is a time consuming and costly task. Using semi supervised learning, it should be possible to label a fraction of the dataset and let the neural network learn by itself on the rest of the, unlabelled, data, thus greatly reducing the overhead of using deep learning technology.
Brain MRI scans are a critical component in the diagnosis of neurodegenerative disorders and their use will only increase in the following years. However, there is a wide diversity in terms of the image quality and resolution obtained across different sites and there is a need for robust methods that can handle such diversity. The goal of this project is to develop and validate the performance of state-of-the-art lesion detection methods for 3D brain MRIs.
Dialogue is a virtual healthcare provider targeted towards the corporate environment. The service promotes employee wellness and productivity by connecting users to qualified healthcare professionals through an online or mobile application. The Dialogue service is increasingly being enhanced by AI techniques to improve user experience and streamline the procedure.
Ce projet de recherche est fait en collaboration avec le département de Recherche et Développement de la compagnie Optimum Réassurance Inc. Il a pour but de faire usage des concepts et des outils d’analyse prédictive, de l’apprentissage automatique et statistique pour développer des méthodes de modélisation et de prédiction des réclamations et des comportements des assurés en assurance voyage. Les données seront fournies par des compagnies d’assurance qui détiennent un contrat de réassurance avec l’organisme partenaire.
Le projet de recherche tente de réduire l’impact de l’absentéisme et des arrêts de travail (chez le personnel de soins) sur la qualité des services proposés dans les hôpitaux. Pour cela, des emplois du temps optimisés seront générés à l’aide de nouveaux indicateurs. Ces indicateurs seront créés avec des algorithmes issus de l’intelligence artificielle à partir des données historiques sur les quarts de travail, dont l’absentéisme et les arrêts de travail.
Currently, testing the population more at risk to be severely ill is a cumbersome process. There is a limit to the capacity and the resources of the healthcare system that show a need to be more efficient in discovering infected person. Being able to quickly detect infected person helps reduce the risk of infecting others and it is especially important in environments like nursing homes where there is a high density of person at risk. Using an earpiece that work as a connected object, it is possible to monitor some signals such as cardiac rhythm, level of CO2, and cough.
By combining the information contained in the visual, audio and text content of videos, it is possible to extract complex information about their content. It’s then possible to analyse a query from a search engine to find the video segments that best matches this query. During this project, the intern will be using state-of-the-art deep learning models to extract the best possible information from multi-source data and participate in the integration of these models in the Grokvideo search engine application.