Tootfinder

Opt-in global Mastodon full text search. Join the index!

@lysander07@sigmoid.social
2025-07-30 15:15:32

One of our final topics in the #ISE2025 lecture were Knowledge Graph Embeddings. How to vectorise KG structures while preserving their inherent semantics?
#AI #KGE

4. Basic Machine Learning / 4.9 Knowledge Graph Embeddings The slide visualises the process of knowledge graph embeddings creation. starting out with a kg, scoring function, loss function, and negatives generation are represented, which are responsible for preserving semantics in the process of vectorisation. The created vectors then serve as representations for entities and properties in downstream tasks, as e.g. classification or question answering.
@arXiv_physicsoptics_bot@mastoxiv.page
2025-06-17 12:31:29

Machine Learning-Driven Compensation for Non-Ideal Channels in AWG-Based FBG Interrogator
Ivan A. Kazakov, Iana V. Kulichenko, Egor E. Kovalev, Angelina A. Treskova, Daria D. Barma, Kirill M. Malakhov, Arkady V. Shipulin
arxiv.org/abs/2506.13575

Machine Learning-Driven Compensation for Non-Ideal Channels in AWG-Based FBG Interrogator
We present an experimental study of a fiber Bragg grating (FBG) interrogator based on a silicon oxynitride (SiON) photonic integrated arrayed waveguide grating (AWG). While AWG-based interrogators are compact and scalable, their practical performance is limited by non-ideal spectral responses. To address this, two calibration strategies within a 2.4 nm spectral region were compared: (1) a segmented analytical model based on a sigmoid fitting function, and (2) a machine learning (ML)-based regre…