Skip to content

Arkady Zgonnikov

Humans, AI, and Oxford commas

  • About
  • Bio
  • Publications
  • Research

About

I am an interdisciplinary cognitive scientist, with a background in applied mathematics, computer science, and cognitive psychology. Currently I am a tenure-track Assistant Professor in Human-Robot Interaction at the Department of Cognitive Robotics, TU Delft.

E-mail: a.zgonnikov at tudelft dot nl
TU Delft | open science framework | github
google scholar | twitter | orcid | researchgate

Arkady Zgonnikov πŸ‡ΊπŸ‡¦ Follow

Assistant professor @tudelft. Cognitive modeling, human-robot interaction, automated driving, meaningful human control over AI

4ester
Retweet on Twitter Arkady Zgonnikov πŸ‡ΊπŸ‡¦ Retweeted
oulasvirta Antti Oulasvirta πŸ‡ΊπŸ‡¦ @oulasvirta ·
54m

This should be obvious, but it isn't: Minimizing RMSE may not be the best way to ensure an ML model behaves in a "human-like" manner.

Quote: "the models [...] struggled at varying degrees to capture the more nuanced courtesy lane change and highway lane change behavior." https://twitter.com/markkula/status/1542148875330490370

Gustav Markkula @markkula

Beyond RMSE: Do machine-learned models of road user interaction produce human-like behavior?

New preprint from our @HFS_ITSLeeds group, led by @SAravindaRK, with our project partners at @_FiveAI

https://arxiv.org/abs/2206.11110

Reply on Twitter 1542151959729373185 Retweet on Twitter 1542151959729373185 3 Like on Twitter 1542151959729373185 4 Twitter 1542151959729373185
Retweet on Twitter Arkady Zgonnikov πŸ‡ΊπŸ‡¦ Retweeted
markkula Gustav Markkula @markkula ·
1h

Beyond RMSE: Do machine-learned models of road user interaction produce human-like behavior?

New preprint from our @HFS_ITSLeeds group, led by @SAravindaRK, with our project partners at @_FiveAI

https://arxiv.org/abs/2206.11110

Reply on Twitter 1542148875330490370 Retweet on Twitter 1542148875330490370 1 Like on Twitter 1542148875330490370 4 Twitter 1542148875330490370
Retweet on Twitter Arkady Zgonnikov πŸ‡ΊπŸ‡¦ Retweeted
artcogsys Artificial Cognitive Systems @artcogsys ·
9h

@Radboud_Uni is hiring 13 assistant professors, also in the field of Artificial Intelligence, ranging from machine learning and reinforcement learning to applications in robotics and sustainability). Application deadline: July 4th! https://www.ru.nl/en/working-at/job-opportunities/assistant-professor-in-social-sciences?s=03

Reply on Twitter 1542025424921923584 Retweet on Twitter 1542025424921923584 4 Like on Twitter 1542025424921923584 5 Twitter 1542025424921923584
Retweet on Twitter Arkady Zgonnikov πŸ‡ΊπŸ‡¦ Retweeted
lilianedwards lilian edwards @lilianedwards ·
25 Jun

This is now my standard example for why it is pointless to restrain regulating "AI' to sophisticated machine learning. Don't regulate AI ; regulate bias, error and ascientific deduction. https://twitter.com/lhreports/status/1540598392300179456

Lighthouse Reports @LHreports

People all over the Netherlands have been flagged for welfare fraud based on a crude spreadsheet & some unscientific prejudices. How do we know? We took the algorithm apart & rebuilt it. Score yourself & see
https://fraudescorekaart.lighthousereports.nl/#/scorekaart

Reply on Twitter 1540648075026436097 Retweet on Twitter 1540648075026436097 39 Like on Twitter 1540648075026436097 124 Twitter 1540648075026436097
Load More...
Copyright © 2022 Arkady Zgonnikov. All Rights Reserved.
Fashify Theme by FRT