Education Research Current About VU Amsterdam NL
Login as
Prospective student Student Employee
Bachelor Master VU for Professionals
Exchange programme VU Amsterdam Summer School Honours programme VU-NT2 Semester in Amsterdam
PhD at VU Amsterdam Research highlights Prizes and distinctions
Research institutes Our scientists Research Impact Support Portal Creating impact
News Events calendar Woman at the top
Israël and Palestinian regions Culture on campus
Practical matters Mission and core values Entrepreneurship on VU Campus
Organisation Partnerships Alumni University Library Working at VU Amsterdam
Sorry! De informatie die je zoekt, is enkel beschikbaar in het Engels.
This programme is saved in My Study Choice.
Something went wrong with processing the request.
Something went wrong with processing the request.

PhD Defence D.W. Romero Guzman 10 September 2024 15:45 - 17:15

Share
The Good, The Efficient and The Inductive Biases

The emergence of Deep Learning has marked a profound shift in the paradigm of machine learning, a change driven by the numerous breakthroughs it has achieved in recent years. However, as the field evolves and Deep Learning becomes increasingly present in everyday tools and applications, there is an increasing need to address unresolved challenges related to its efficiency and sustainability. This dissertation delves into the role of inductive biases, particularly continuous modeling and symmetry preservation, to address these challenges and enhance the efficiency of Deep Learning. The dissertation is structured in two main parts. The first part investigates continuous modeling as a tool to improve the efficiency of Deep Learning algorithms. Continuous modeling involves the idea of parameterizing neural operations directly in a continuous space. The research presented in this part highlights the substantial benefits of continuous modeling for the (i) computational efficiency –in time and memory–, (ii) the parameter efficiency, and (iii) the complexity of designing neural architectures for new datasets and tasks, coined "design efficiency". In the second half, the focus shifts towards the influence of symmetry preservation on the efficiency of Deep Learning algorithms. Symmetry preservation involves designing neural operations that align with the inherent symmetries of data. The research presented in this part highlights significant gains both in data and parameter efficiency through the use of symmetry preservation. However, it also acknowledges a resulting trade-off of increased computational costs. The dissertation concludes with a thorough critical evaluation of the research findings, openly discussing their limitations and proposing strategies to address them, informed by literature and the author's insights. It ends by identifying promising future research avenues in the exploration of inductive biases for efficiency, and their wider implications for Deep Learning.

More information on the thesis

Programme

PhD defence by D.W. Romero Guzman

Faculty of Science

Supervisors:

  • prof.dr. M. Hoogendoorn
  • dr. J.M. Tomczak
  • dr. E.J. Bekkers

The PhD defence can also be followed online.

About PhD Defence D.W. Romero Guzman

Starting date

  • 10 September 2024

Time

  • 15:45 - 17:15

Location

  • Auditorium, Hoofdgebouw

Address

  • De Boelelaan 1105
  • 1081 HV Amsterdam

Follow the defence online

Go to livestream

Quick links

Homepage Culture on campus VU Sports Centre Dashboard

Study

Academic calendar Study guide Timetable Canvas

Featured

VUfonds VU Magazine Ad Valvas Digital accessibility

About VU

Contact us Working at VU Amsterdam Faculties Divisions
Privacy Disclaimer Veiligheid Webcolofon Cookies Webarchief

Copyright © 2025 - Vrije Universiteit Amsterdam