Recent seminars

Europe/Lisbon
Online

Pedro Domingos

Pedro Domingos, University of Washington
Deep Networks Are Kernel Machines

Deep learning's successes are often attributed to its ability to automatically discover new representations of the data, rather than relying on handcrafted features like other learning methods. In this talk, however, I will show that deep networks learned by the standard gradient descent algorithm are in fact mathematically approximately equivalent to kernel machines, a learning method that simply memorizes the data and uses it directly for prediction via a similarity function (the kernel). This greatly enhances the interpretability of deep network weights, by elucidating that they are effectively a superposition of the training examples. The network architecture incorporates knowledge of the target function into the kernel. The talk will include a discussion of both the main ideas behind this result and some of its more startling consequences for deep learning, kernel machines, and machine learning at large.

Additional file

document preview

Domingos_P.pdf

Europe/Lisbon
Online

Francisco Förster Burón

Francisco Förster Burón, Universidad de Chile
The ALeRCE astronomical alert broker

A new generation of large aperture and large field of view telescopes is allowing the exploration of large volumes of the Universe in an unprecedented fashion. In order to take advantage of these new telescopes, notably the Vera C. Rubin Observatory, a new time domain ecosystem is developing. Among the tools required are fast machine learning aided discovery and classification algorithms, interoperable tools to allow for an effective communication with the community and follow-up telescopes, and new models and tools to extract the most physical knowledge from these observations. In this talk I will review the challenges and progress of building one of these systems: the Automatic Learning for the Rapid Classification of Events (ALeRCE) astronomical alert broker. ALeRCE is an alert annotation and classification system led by an interdisciplinary and interinstitutional group of scientists from Chile since 2019. ALeRCE is focused around three scientific cases: transients, variable stars and active galactic nuclei. Thanks to its state-of-the-art machine learning models, ALeRCE has become the 3rd group to report most transient candidates to the Transient Name Server, and it is enabling new science with different astrophysical objects, e.g. AGN science. I will discuss some of the challenges associated with the problem of alert classification, including the ingestion of multiple alert streams, annotation, database management, training set building, feature computation and distributed processing, machine learning classification and visualization, or the challenges of working in large interdisciplinary teams. I will also show some results based on the real‐time ingestion and classification using the Zwicky Transient Facility (ZTF) alert stream as input, as well as some of the tools available.

Europe/Lisbon
Online

Olga Mula

Olga Mula, TU Eindhoven
Optimal State and Parameter Estimation Algorithms and Applications to Biomedical Problems

In this talk, I will present an overview of recent works aiming at solving inverse problems (state and parameter estimation) by combining optimally measurement observations and parametrized PDE models. After defining a notion of optimal performance in terms of the smallest possible reconstruction error that any reconstruction algorithm can achieve, I will present practical numerical algorithms based on nonlinear reduced models for which we can prove that they can deliver a performance close to optimal. The proposed concepts may be viewed as exploring alternatives to Bayesian inversion in favor of more deterministic notions of accuracy quantification. I will illustrate the performance of the approach on simple benchmark examples and we will also discuss applications of the methodology to biomedical problems which are challenging due to shape variability.

https://arxiv.org/pdf/2203.07769.pdf
https://arxiv.org/pdf/2009.02687.pdf