Derek S. Prijatelj
@derekprijatelj.bsky.social
Researcher of info theory & machine learning
Complex systems enthusiast
Ph.D. @ University of Notre Dame
Complex systems enthusiast
Ph.D. @ University of Notre Dame
If you're interested in understanding the logic behind how to detect novelty from determinism to PAC-Bayes Learning, we have a preprint at arxiv.org/abs/2501.09331. The reasoning is grounded in computation and information theory.
Identifying Information from Observations with Uncertainty and Novelty
A machine learning tasks from observations must encounter and process uncertainty and novelty, especially when it is to maintain performance when observing new information and to choose the hypothesis...
arxiv.org
August 16, 2025 at 7:45 PM
If you're interested in understanding the logic behind how to detect novelty from determinism to PAC-Bayes Learning, we have a preprint at arxiv.org/abs/2501.09331. The reasoning is grounded in computation and information theory.
The paper is at doi.org/10.1613/jair.... the benchmarks starts with Kinetcs400, then splits Kinetics600 and 700 into 5 increments each, where new activities are introduced and to be detected & learned. We limit the feedback to see which samples the predictor prioritizes for ground truth labels.
Human Activity Recognition in an Open World
| Journal of Artificial Intelligence Research
doi.org
August 16, 2025 at 7:43 PM
The paper is at doi.org/10.1613/jair.... the benchmarks starts with Kinetcs400, then splits Kinetics600 and 700 into 5 increments each, where new activities are introduced and to be detected & learned. We limit the feedback to see which samples the predictor prioritizes for ground truth labels.