Dear all, Roman Ziske will deliver the next Oberseminar (16th January,10:00, via Zoom): Title: „Exploring Self-Supervised Learning for Wideband Radio Frequency Signal Recognition“ Abstract: Recent advancements in Radio Frequency Machine Learning (RFML) have shown promising results in varios wireless applications. However, the field faces significant challenges due to the scarcity of high-quality labeled RF data. While Self-Supervised Learning (SSL) has emerged as a potential solution, demonstrated by success in other domains like Computer Vision and Natural Language Processing, current RFML research on SSL is limited to simple signal classification tasks and small-scale datasets. This research investigates the applicability of SSL pretraining for more complex tasks, specifically signal recognition which consist of detection, localization in time and frequency, and classification of signals in the wideband RF spectrum. Therefore, existing approaches will be scaled to larger datasets to learn more robust features, and different SSL frameworks will be evaluated for signal recognition performance. **We cordially ask the attendees to turn on their cameras and turn off their microphones during the presentation. Zoom Room: https://eur05.safelinks.protection.outlook.com/?url=https%3A%2F%2Ffernuni-hagen.zoom.us%2Fj%2F62388524887%3Fpwd%3DWmJRRUpDZWZ4WlJoeFlGQTBESWplQT09&data=05%7C02%7Csteffi.bluemel%40fernuni-hagen.de%7C42fe776c1f324ba6b7aa08dc223844de%7Cc2bba033db424b299adb6ac379499ef7%7C1%7C0%7C638422872265614676%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=X%2F4UFs7fFH%2BIDLw7SsgOOqv3FUyNoCPE7k9B7YFDaGE%3D&reserved=0<https://fernuni-hagen.zoom.us/j/62388524887?pwd=WmJRRUpDZWZ4WlJoeFlGQTBESWplQT09> --- Current Scheduled Talks ---- * 16th January, Roman Ziske, MSc proposal * 23rd January, Theodoros Doukas, MSc defense * 13th February, Armin Sdorra, MSc defense * 20th March, Jean-Guy Mailly, invited speaker If you do not wish to receive messages from this mailing list anymore, please let me know by simply responding „unsubscribe“ to this mail (steffi.bluemel@fernuni-hagen.de<mailto:steffi.bluemel@fernuni-hagen.de>). Best regards, Steffi Blümel - Sekretariat - ---------------------------------------------------- FernUniversität in Hagen Fakultät Mathematik und Informatik / Lehrgebiet Künstliche Intelligenz Universitätsstraße 1 58097 Hagen Fon: + 49 23 31 - 9 87 40 06 E-Mail: steffi.bluemel@fernuni-hagen.de<mailto:steffi.bluemel@fernuni-hagen.de>