Open Position: PhD Position - Deep meta-learning on learning curves to improve machine learning

Challenge: Developing deep meta-learning algorithms to model and understand learning curve patterns in machine learning.

Impact: Faster, better, more cost-efficient training and tuning of learning

Read the vacancy text

Publications and Preprints

A Survey of Learning Curves with Bad Behavior: or How More Data Need Not Lead to Better Performance
Marco Loog, Tom Viering
Benelearn, 2022

LCDB 1.0: An extensive Learning Curves Database for Classification Tasks
Felix Mohr, Tom Viering, Marco Loog, Jan N Van Rijn
ECML 2022
code slides poster

Different Approaches to Fitting and Extrapolating the Learning Curve
D Kim, T Viering, (student paper)
Benelearn 2022,

To Tune or not to Tune: Hyperparameter Influence on the Learning Curve
P Bhaskaran, T Viering (student paper)
Benelearn 2022,

The Shape of Learning Curves: a Review
Tom Viering, Marco Loog
TPAMI 2022
code

A Brief Prehistory of Double Descent
Marco Loog, Tom Viering, Alexander Mey, Jesse H. Krijthe, David M.J. Tax
PNAS 2020

Making Learners (More) Monotone
Tom Viering, Alexander Mey, Marco Loog
IDA 2020
code slides video

A Brief Prehistory of Double Descent
Marco Loog, Tom Viering, Alexander Mey, Jesse H. Krijthe, David M.J. Tax
arxiv preprint 2020

A Distribution Dependent and Independent Complexity Analysis of Manifold Regularization
Alexander Mey, Tom Julian Viering, Marco Loog
IDA 2020

Is Wikipedia succeeding in reducing gender bias? Assessing changes in gender bias in Wikipedia using word embeddings
Katja Geertruida Schmahl, Tom Julian Viering, Stavros Makrodimitris, Arman Naseri Jahfari, David Tax, Marco Loog (student paper),
NLP CSS 2020

How to Manipulate CNNs to Make Them Lie: the GradCAM Case
Tom Viering, Ziqi Wang, Marco Loog, Elmar Eisemann
arxiv preprint 2019
slides

Minimizers of the Empirical Risk and Risk Monotonicity
Marco Loog, Tom Viering, Alexander Mey
in NeurIPS 2019
code slides poster

Nuclear discrepancy for single-shot batch active learning
Tom J Viering, Jesse H Krijthe, Marco Loog
in Machine Learning 2019
code slides poster

Open Problem: Monotonicity of Learning
T Viering, A Mey, M Loog
in COLT 2019

Talks

In my lab, we often give short talks about selected papers we like. You can find the papers I've given talks about below.

Teaching Experience

Assistant Professor @TU Delft

JAN 2023 - NOW

My focus is on education innovation and learning curve research. With regards to education innovation, we are working to create a community for machine learning teachers in TU Delft to improve collaborations in teaching and to kickstart developing open education material for reuse. In my teaching I like to employ interactive Python widgets in my class to stimulate students' understanding and am interested in developing more interactive education.

Lecturer @TU Delft

NOV 2020 - DEC 2022

I helped develop the new AI minor program which started in September 2021. For this program I have developed two courses from scratch and lectured them: 'Introduction to Machine Learning' (TI3145TU) and 'Capstone Applied AI project' (TI3150TU). In this program engineers with various backgrounds learn the basics of AI and machine learning, and apply the learned techniques in the field for their major.

I am also involved in the Master elective Fundamentals of Artificial Intelligence, and have developed a MOOC (Massive Online Open Course) on Supervised Machine Learning together with Hanne Kekkonen. In collaboration with other lecturers we have designed a second MOOC on unsupervised learning, reinforcement learning and deep learning.

Education

PhD On Safety in Machine Learning @TU Delft

OCT 2016 - MAY 2023

Supervisor: Marco Loog, Promotor: Elmar Eiseman.
My PhD focused on three theoretical machine learning topics: explainability, active learning and learning curves. The main take-aways are (TLDR):
- Strictly tighter generalization bounds do not imply better performance.
- Explanations provided by Grad-CAM can be misleading.
- Even in simple settings more data can lead to worse performance.
- We provide ideas to construct learners that always improve with more data.

On Safety in Machine Learning (PhD Thesis PDF)
Tom Viering
TU Delft 2023
cover summary propositions

Master Computer Science @TU Delft

SEP 2013 - AUG 2016

Supervisor: Marco Loog.
During my masters in Delft I discovered my passion for Machine Learning. I spent a long time on my masters project, simply because I loved it so much. My supervisors were Marco Loog and Jesse Krijthe, and we studied the problem of Active Learning using generalization bounds, in particular using the Discrepancy measure.

Active Learning by Discrepancy Minimization: A Comparison of Active Learning Methods Motivated by Generalization Bounds (MSc Thesis PDF)
T J Viering
masterthesis 2016
abstract

Bachelor Physics @Leiden University

SEP 2009 - AUG 2013

While I really enjoyed physics in my bachelor, in the end of my bachelor I fell in love with computer science (CS). During my bachelor project I built an application to control an electron microscope (EM) to record a giant mosaic of images as fast and accurate as possible. I also worked together with Frank Faas to develop a basic application to annotate and view gigabyte-size EM images. You can view the zebrafish dataset of the KosterLab research group here, which was in part annotated with help of software that Frank and I wrote. I spent the fourth year of my (physics) bachelor studying Computer Science in order to switch to my CS master at TU Delft.

Interests

Social Media