Derek S. Prijatelj

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...

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.

16.08.2025 19:45 — 👍 2    🔁 0    💬 0    📌 0

Human Activity Recognition in an Open World | Journal of Artificial Intelligence Research

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.

16.08.2025 19:43 — 👍 0    🔁 0    💬 1    📌 0

A modified Uncle Sam pointing at viewer with a question mark in place for a head asking "Can your AI learn novelty?"

Can your AI learn novelty? I'm presenting at @ijcai.org an incremental online learning benchmark where novel classes are introduced in each increment with prior known classes. Come talk with me at #IJCAI2025 about predictor detection & adaptation to novel phenomena! 😁

16.08.2025 19:34 — 👍 3    🔁 2    💬 1    📌 0