Applications of Singularity Theory on Deep Neural Network.

(Fapesp process number: 2019/08939-0)


The purpose of this project is to determine singularities on deep neural networks using the math machinery from Singularity Theory and Applied Mathematics. Such singularities exist due to issues in the training data, training algorithm, network architecture, algorithm parameters, etc. Singularities can result in adversarial inputs that can destabilize the output of the network; singularities can also cause instability in the training process.





Brazil-US SPRINT Project


The SPRINT - São Paulo Researchers in International Collaboration, a strategy designed to encourage and promote the advancement of scientific research through the engagement of researchers affiliated with research institutions in the State of São Paulo with researcher partners abroad.

Next Event:


    (Soon!)

  • Title: Complex systems: modeling, prediction and applications.
    Speaker: Dr. Francisco A. Rodrigues - ICMC-USP-Brazil

    Date of Event: 28/09/2021

    Time: 4PM - 5:10PM EDT

    Abstract Available Here. Speaker's Biography: Here.

    Click here to join the meeting!




Upcoming Events:

(Dates to be assigned.)


  • Mini-course: Introduction to Neural Networks.

  • Mini-course: Introduction to Singularity Theory.




Past Events: