Konstantinos (Kokos) Kogkalidis
On Mondays and Tuesdays I am a ML research scientist by Skyfora, where I'm doing climate stuff with neural networks. During the rest of the week I am a post-doctoral researcher in Aalto University, doing neurosymbolic machine learning. Before moving to Finland, I received both my PhD (CompLing) and my master's degree (AI) from Utrecht University. While in Utrecht, I was also working remotely as a machine learning engineer at geekbot.io. Before all that, I received my diploma in Electrical & Computer Engineering from the Aristotle University of Thessaloniki.
My published research revolves around structured machine learning, neurosymbolic reasoning, and type-driven approaches to syntactic parsing and semantic compositionality, among others.
I am especially interested in the interface between formal and data-driven methods;
if that floats your boat rubber duck, you can have a look at my publications page.
Thesis
My dissertation, titled Dependency as Modality, Parsing as Permutation: A Neurosymbolic Perspective on Categorial Grammars, introduces a modal extension to type-logical grammars, aimed at capturing dependency roles. It explores the parsing-as-deduction paradigm, but from the angle of a machine learning practitioner. You can find a faithful copy of the physical print here. If (for whatever reason) you're interested in an actual physical copy, feel free to send me a message.Recent & Upcoming Talks
Here's a list of my recent and upcoming talks (more here):-
September 12, 2023 in GöteborgPresentation @ Learning with Small Data
-
September 11, 2023 in GöteborgPoster @ Learning with Small Data
-
May 3, 2023 in Dubrovnik
-
September 16, 2022 in ComoPresentation @ Logic for the AI Spring
Teaching
- Compositional Models of Vector-Based Semantics (ESSLLI 2022, lecture)
- Logic & Language (2018-2019, 2019-2020, 2021-2022, lectures & project supervision)
- Machine Learning for Human Vision & Language (2019-2020, tutorials)
- Advanced Topics in Cognitive Modelling (2018-2019, tutorials)