Third-year PhD student in machine learning at Rutgers University. My research interests are machine learning and computer vision.
Machine Learning, Deep Learning, Keras, Computer Vision, Generative Adversarial Networks (GANs), Sklearn, Python, Artificial Intelligence, Robotics.
(Distinction) Master of Science in Technology - Security and Mobile Computing - Helsinki University of Technology, Helsinki, Finland 2006 – 2008
Master of Science, Information Technology - Royal Institute of Technology, Stockholm, Sweden 2006 – 2008
(Valedictorian) Bachelor of Science, Informatics - University of Tirana, Tirana, Albania 2001 – 2006
Patent: 2013. User interface for emergency alert system. U.S. Patent 8,533,612, filed Jun. 7, 2010, and issued September 10, 2013
Blerta Lindqvist, Shridatt Sugrim, Rauf Izmailov - "AutoGAN: Robust Classifier Against Adversarial Attacks".
Rauf Izmailov, Blerta Lindqvist, Peter Lin - “Feature Selection in Learning Using Privileged Information”, IEEE International Conference on Data Mining Workshop on Data-driven Discovery of Models (D3M), 2017.
Konstantinos Michmizos, Blerta Lindqvist, Stephen Wong, Eric L. Hargreaves, Konstantinos Psychas, Georgios D. Mitsis, Shabbar F. Danish, Konstantina S. Nikita - “Computational Neuromodulation: Future Challenges for Deep Brain Stimulation”, IEEE Signal Processing Magazine, 2017.
Machine Learning Intern, Perspecta Labs, NJ, Jun 2018 – Aug 2018
Working on adversarial machine learning, I developed a novel way to counter adversarial attacks that is able to handle different kinds and magnitudes of attack. In addition, it defends effectively even in the lack of adversarial training points. Accuracy on MNIST dataset exceeds FGSM method for different magnitudes of attack for training and testing.
Machine Learning Intern, Vencore Labs, NJ, Jun 2017 – Aug 2017
Improved classification results of various datasets by utilizing mutual information between features. We generated new features as regressions of each existing feature from the rest of the features and then achieved better classification results from all features combined. The top improvement on the error was over 27% points.
Deep Learning R&D Intern, Nvidia, NJ, Jun 2016 – Sept 2016
Working with Nvidia's autonomous driving team, I applied regularization to the deep learning network resulting in a decrease of 91% in the size of the network performance, accuracy improvement of 8% points and reduced over-fitting. The decrease in network size that I implemented was critical to the project because it decreased the memory required for deploying the autonomous driving solution. I also led efforts for a crucial component of the learning system towards its reliability, innovating two metrics for establishing a reliability estimate for the output of the model.