I’m a principal research engineer with Ph.D. degree in Electrical and Computer Engineering. My interests include Machine Learning applied to Natural Language Processing, Automatic Speech Recognition and Computer Vision.
In addition to some theoretical analyses of existing Machine Learning models, such as bounds on the false
and truth positive rates based on a VC-style analysis, I invented Machine Learning algorithms that have been applied to problems in different areas by many other researchers, of which I highlight maximum margin training methods for neural networks, such as the Maximum-margin GDX (MMGDX) and Support Vector Neural Networks (SVNN). Continual learning is the central theme of my current research activity, from biologically inspired methods to new mathematically grounded fine-tuning algorithms that can be applied like any other PyTorch optimizer class. You can find other contributions on my Google Scholar profile, and codes available on GitHub and Mathworks.
I work with multimodal large language models and automatic speech recognition for the automotive industry at Cerence AI.