no code implementations • 26 Dec 2023 • Erik Derner, Dalibor Kučera, Nuria Oliver, Jan Zahálka
We compare the personality trait estimations made by ChatGPT against those by human raters and report ChatGPT's competitive performance in inferring personality traits from text.
no code implementations • 19 Nov 2023 • Erik Derner, Kristina Batistič, Jan Zahálka, Robert Babuška
As large language models (LLMs) permeate more and more applications, an assessment of their associated security risks becomes increasingly necessary.
no code implementations • 13 May 2023 • Erik Derner, Kristina Batistič
The increasing popularity of large language models (LLMs) such as ChatGPT has led to growing concerns about their safety, security risks, and ethical implications.
no code implementations • 1 Feb 2023 • Jiří Kubalík, Erik Derner, Robert Babuška
Symbolic regression is a method that can automatically generate such models from data.
1 code implementation • 31 May 2022 • Martin Vastl, Jonáš Kulhánek, Jiří Kubalík, Erik Derner, Robert Babuška
The task of finding formulas from a set of observed inputs and outputs is called symbolic regression.
1 code implementation • 18 Mar 2022 • Jonáš Kulhánek, Erik Derner, Torsten Sattler, Robert Babuška
We propose a 2D-only method that maps multiple context views and a query pose to a new image in a single pass of a neural network.
2 code implementations • 21 Oct 2020 • Jonáš Kulhánek, Erik Derner, Robert Babuška
This precludes the use of the learned policy on a real robot.
1 code implementation • 8 Aug 2019 • Jonáš Kulhánek, Erik Derner, Tim de Bruin, Robert Babuška
However, the application of deep RL to visual navigation with realistic environments is a challenging task.
1 code implementation • 27 Mar 2019 • Erik Derner, Jiří Kubalík, Nicola Ancona, Robert Babuška
We demonstrate on a real pendulum system that the analytic model found enables a RL controller to successfully perform the swing-up task, based on a model constructed from only 100 data samples.
no code implementations • 22 Mar 2019 • Jiří Kubalík, Erik Derner, Jan Žegklitz, Robert Babuška
Reinforcement learning algorithms can solve dynamic decision-making and optimal control problems.