Projects

ANTIPASTI is a Python Deep Learning method that predicts the binding affinity of antibodies from their three-dimensional structure.

STARlet REgularized Deconvolution (STARRED) is a Python two-channel deconvolution method powered by Starlet regularization and JAX automatic differentiation. It uses a Point Spread Function (PSF) narrower than the original one as kernel.

Model for domestic sounds classification. Third year project of the engineering degree at IMT Atlantique.

Comparison between Learnlets, a neural network that learns filter banks in a denoising setting with backpropagation and gradient descent, and U-nets.

Design and validation of a Class-D audio amplifier.

Academic project in Argentina. Design and construction of a functional humidity sensor.