Events

Machine Learning Coffee seminar: "Infinitely deep models with continuous-time flows" Markus Heinonen

Helsinki region machine learning researchers will start our week by an exciting machine learning talk. The aim is to gather people from different fields of science with interest in machine learning. Porridge and coffee is served at 9:00 and the talk will begin at 9:15.
Speech Recognizer Board, professor Teuvo Kohonen, 1980

Infinitely deep models with continuous-time flows

Markus Heinonen
Academy of Finland Postdoctoral Fellow, Aalto University

Abstract: Bayesian formalism has recently entered the age of deep models. Deep generative models, such as VAEs, learn unimodal variational representations of complex data objects. Paired with Normalising flows these variational approximations can be successively transformed to the more powerful family of multimodal distributions. Similarly in predictive modelling stacking Gaussian processes into ‘layers’ produces a deep predictive models with increased capacity and multimodality. Both of these approaches are based on evolving random variables with discrete-time transformations, which are seriously hindered by the theoretical requirement of invertibility. We propose a novel paradigm of continuous time ‘flows’ that generalises the concept of discrete transformations into infinite continuous domain. We derive theory from fluid dynamics that does not require invertible transformations. We demonstrate initial results, which exceed the state-of-the-art.

Please spread the news and join us for our weekly habit of beginning the week by an interesting machine learning talk!

Subscribe to the mailing list where seminar topics are announced beforehand or check out the next talks at the seminar webpage.

Welcome!

 

Other events

SpecialSeminar_AaltoEvent
Lectures and seminars

CS Special Seminar: Mikko Kiviharju "Putting crypto back into cyber"

This talk is arranged at the Department of Computer Science.
SpecialSeminar_AaltoEvent
Lectures and seminars

CS Special Seminar: Philip Ginzboorg "Creating and Using Security Infrastructures"

This talk is arranged at the Department of Computer Science.
Doctoral theses hanging on the wall
Public defences

Public defence in Computer Science, Julie Meyer

Title of the doctoral thesis: Numerical and perceptual evaluations of finite-difference time-domain simulations for room acoustics applications
Doctor's hat
Public defences

Public defence in Computer Science, Matti Huotari

Title of the doctoral thesis: Machine Learning Applications for Energy Utilization of Smart Buildings
  • Published:
  • Updated:
Share
URL copied!