MLGdańsk #139 – DCID: Deep Canonical Information Decomposition

Serdecznie zapraszamy na 139. spotkanie MLGdańsk – Poniedziałek, 17 kwietnia 2023 o godzinie 18.00 CET.

Link do spotkania:
https://meet.jit.si/MLGdansk_20032023_nb139

Prelegentem będzie:
Alexander Rakowski
Hasso Plattner Institute, Poczdam
https://hpi.de/research-schools/hpi-dse/mitglieder/research-pages/alexander-rakowski.html

Temat spotkania:
DCID: Deep Canonical Information Decomposition

Opis prelekcji
“We consider the problem of separating the signal shared between two scalar variables, from their individual signals. In the case of non-scalar, multivariate variables, the probabilistic interpretation of CCA allows to retrieve the shared signal. However, in the univariate case, CCA can only yield trivial solutions. Inspired by the field of Deep Multi-Task Learning, we propose to overcome this problem by approximating the variables of interest with Deep Neural Network classifiers and using their latent features as multivariate decompositions of the variables, allowing us to utilize the standard CCA machinery to discover the shared signal.

Serdecznie zapraszamy – spotkanie otwarte dla wszystkich zainteresowanych!