Homepage Inria website
  • Inria login
  • The Inria's Research Teams produce an annual Activity Report presenting their activities and their results of the year. These reports include the team members, the scientific program, the software developed by the team and the new results of the year. The report also describes the grants, contracts and the activities of dissemination and teaching. Finally, the report gives the list of publications of the year.

  • Legal notice
  • Cookie management
  • Personal data
  • Cookies

Section: Partnerships and Cooperations

International Research Visitors


From May to August 2018 we hosted Devang Kulshreshtha, a computer science student from the Indian Institute of Technology (BHU) Varanasi, who worked on “Debugging Deep Learning Algorithms via Pattern Mining Methods”. His work aimed at mining patterns of neuron activation that precede misclassifications in deep neural networks (DNN). The goal of this effort is to predict when a DNN will likely err. This can be used e.g., to obtain hints on how to retrain the network to improve its accuracy.