ML for the Sciences

  • Deep convolutional neural networks for multi-scale time-series classification in fusion devices

    Fri, Feb 14, 2020, 12:30 pm

    The multi-scale, mutli-physics nature of fusion plasmas makes predicting plasma events challenging. Recent advances in deep convolutional neural network architectures (CNN) utilizing dilated convolutions enable accurate predictions on sequences which have long-range, multi-scale characteristics, such as the time-series generated by diagnostic instruments observing fusion plasmas.

  • Generalized Lagrangian Networks

    Fri, Jan 31, 2020, 12:00 pm

    Even though neural networks enjoy widespread use, they still struggle to learn the basic laws of physics. How might we endow them with better inductive biases? Recent work (Greydanus et al. 2019) proposed Hamiltonian Neural Networks (HNNs) which can learn the Hamiltonian of a physical system from data using a neural network. A key issue with these models is that they require a priori knowledge of the system’s conjugate position and momentum coordinates, and thus are difficult to learn from arbitrary coordinates such as pixels.

  • Solving Inverse Problems with Data-driven Priors

    Fri, Jan 17, 2020, 12:00 pm

    I will present a Bayesian machine learning architecture that combines a physically motivated parameterization and an analytic error model for the likelihood with a deep generative model providing a powerful data-driven prior for complex signals. This combination yields an interpretable and differentiable generative model, allows the incorporation of prior knowledge, and can be utilized for observations with different data quality without having to retrain the deep network.

  • Machine Learning for the Sciences

    Repeats every 2 weeks every Friday until Fri Dec 13 2019 except Fri Nov 29 2019.
    Fri, Oct 18, 2019, 12:00 pm

    Taking place every other Friday. Lunch will be provided.

    This interdisciplinary meeting focusses on ML approaches that are useful for the sciences and engineering. The style is informal, a mix of journal club, practical tutorials, and project discussion from the participants. Join us if you want to learn new ML approaches for scientific research and, in particular, if you're already using them.

Subscribe to ML for the Sciences