Visualising Deep Network’s Time-Series Representations
2021 · arXiv preprint · Błażej Leporowski and Alexandros Iosifidis · Time-series representation analysis.
Background
Technical judgment built across systems and research.
I work on AI systems where data, evaluation, infrastructure, and human judgment must hold together.
Current practice
From technical direction through delivery.
I work directly on production AI systems across product and engineering teams: system design, LLM and retrieval workflows, data pipelines, backend services, deployment, and technical delivery. This is anonymised role and system evidence, not a claim about a named client or product.
External career record: LinkedIn
Research background
Methods before claims.
Selected publications reflect prior work in machine learning, anomaly detection, computer vision, and time-series analysis. They show technical foundations; they are not presented as evidence of current client outcomes.
Research record
Selected publications
Research record: Google Scholar
DeepTimeAnomalyViz: A Tool for Visualizing and Post-processing Deep Learning Anomaly Detection Results for Industrial Time-Series
2021 · arXiv preprint · Błażej Leporowski, Casper Hansen, and Alexandros Iosifidis · Visualization, comparison, and post-processing for industrial anomaly detection.
Detecting Faults during Automatic Screwdriving: A Dataset and Use Case of Anomaly Detection for Automatic Screwdriving
2021 · arXiv preprint · Błażej Leporowski, Daniella Tola, Casper Hansen, and Alexandros Iosifidis · Applied anomaly detection for industrial processes.
Audio-visual Dataset and Method for Anomaly Detection in Traffic Videos
2023 · arXiv preprint · Arian Bakhtiarnia, Błażej Leporowski, Lukas Esterle, and Alexandros Iosifidis · Computer-vision and audio-visual anomaly detection.
Current work