The learning approach will be very hands on, so participants will need to bring laptops. There will be a series of exercises and challenges to work through, while being aided by experts on Python (Dr Prasun Ray) and machine learning for acoustics (Ramon Fuentes). There will also be some seminars on Neural Networks.
The workshop will examine how to plan experiments in order to use information in a cost-optimal way. It will also include the application of these modalities to training complex models, such as deep architectures, and the transfer of these ideas to the generation of physically-relevant complex structures such as chemical structures, molecular structures, scalar or vector fields in fluid dynamics or electrodynamics, proposal steps for Markov chain Monte Carlo of physical systems etc.
The workshop will include methods to summarize and interpret a complicated learned model (e.g. deep neural network) by interrogating this model about what and why it has learned (e.g. relevance propagation and sensitivity analysis).
This workshop will showcase how to employ mathematical aspects of statistical / information theoretic approaches in ML for the discovery of physical laws from data. Offering statistical guarantees along with the learned models is critical in physics and in areas such as aeronautics, climate science, chemistry, biology, and robotics. We will consider model selection, robust statistics, model-free and adaptive learning, and model validation in the context of both static and dynamic models, such as equations of motion.
In this workshop we will explore how to use physical intuition and ideas to design new classes of machine learning (ML) algorithms. Physics-inspired sampling algorithms could be used to train ML structures or sample the hyper-parameter space (e.g. deep Neural Networks). Additionally, physics-based models such as Ising/Potts models or energy-based models have influenced ML inference frameworks such as Markov Random Fields and Restricted Boltzmann Machines, and we want to continue the discussion to facilitate this innovation transfer. Finally, physical insight could be used to enhance learning in the situation of scarce data by enforcing smoothness, differentiability or other physical properties relevant to a given problem.
Conference-Service.com offers, as part of its business activities, a directory of upcoming scientific and technical meetings. The calendar is published for the convenience of conference participants and we strive to support conference organisers who need to publish their upcoming events. Although great care is being taken to ensure the correctness of all entries, we cannot accept any liability that may arise from the presence, absence or incorrectness of any particular information on this website. Always check with the meeting organiser before making arrangements to participate in an event!