Published in Towards Data Science·PinnedNeural ODEs with PyTorch Lightning and TorchDynEffortless, Scalable Training of Neural Differential Equations — Traditional neural network models are composed of a finite number of layers. Neural Differential Equations (NDEs), a core model class of the so-called continuous-depth learning framework, challenge this notion by defining forward inference passes as the solution of an initial value problem. This effectively means that NDEs can be thought…Deep Learning6 min read
Published in Towards Data Science·Nov 21, 2019Graph Neural Ordinary Differential EquationsExtending Graph Neural Networks into a continuous depth domain — Multi — agent systems are prevalent across a variety of scientific fields: from physics to robotics, game-theory, finance and molecular biology, among others. Often, closed — form analytic formulations are not available and forecasting or decision making tasks have to rely on noisy, irregularly sampled observations. This class of systems…Machine Learning10 min read
Sep 9, 2018Spearman’s rho. Why the 6?Just the other day I came across this formula during one of my graduate classes: As someone with a background in control theory and deep learning I am very used to having my formulas work for arbitrary coefficients. You know, I like my deltas, epsilons and alphas. Of course, for…Programming4 min read
