Künstliche Intelligenz und Big Data
Refine
Document Type
- Conference Proceeding (7)
- Article (4)
- Preprint (2)
- Workingpaper / Report (2)
Language
- English (12)
- Multiple languages (2)
- German (1)
Is part of the Bibliography
- yes (15)
Keywords
- Maschinelles Lernen (9)
- Künstliche Intelligenz (3)
- Datenanalyse (2)
- Digitales Archiv (2)
- Generative Design (2)
- Generative Logic (2)
- Intermedialität (2)
- Lenses (2)
- Logic Programming (2)
- Maschinelles Sehen (2)
Department/institution
The Simple Generative Logic Grammar (SGLG) is a newly developed, very simply structured type of logic grammar designed for generating structured visual compositions. This paper examines its key features and explores its potential to play a central role in the educational framework Exploring Generative Logic (EGL) that I am currently developing. [1] At the heart of EGL is the idea of using the artistic creation of images composed of discrete elements to introduce students particularly in art and design to fundamental concepts in logic programming, formal grammars, and database systems in an accessible way.
Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models
(2025)
The discovery and identification of molecules in biological and environmental samples is crucial for advancing biomedical and chemical sciences. Tandem mass spectrometry (MS/MS) is the leading technique for high-throughput elucidation of molecular structures. However, decoding a molecular structure from its mass spectrum is exceptionally challenging, even when performed by human experts. As a result, the vast majority of acquired MS/MS spectra remain uninterpreted, thereby limiting our understanding of the underlying (bio)chemical processes. Despite decades of progress in machine learning applications for predicting molecular structures from MS/MS spectra, the development of new methods is severely hindered by the lack of standard datasets and evaluation protocols. To address this problem, we propose MassSpecGym -- the first comprehensive benchmark for the discovery and identification of molecules from MS/MS data. Our benchmark comprises the largest publicly available collection of high-quality labeled MS/MS spectra and defines three MS/MS annotation challenges: de novo molecular structure generation, molecule retrieval, and spectrum simulation. It includes new evaluation metrics and a generalization-demanding data split, therefore standardizing the MS/MS annotation tasks and rendering the problem accessible to the broad machine learning community. MassSpecGym is publicly available at this https URL [https://github.com/pluskal-lab/MassSpecGym].
Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models
(2025)
Deep neural networks (DNNs) have proven to be successful in various computer vision applications such that models even infer in safety-critical situations. Therefore, vision models have to behave in a robust way to disturbances such as noise or blur. While seminal benchmarks exist to evaluate model robustness to diverse corruptions, blur is often approximated in an overly simplistic way to model defocus, while ignoring the different blur kernel shapes that result from optical systems. To study model robustness against realistic optical blur effects, this paper proposes two datasets of blur corruptions, which we denote OpticsBench and LensCorruptions. OpticsBench examines primary aberrations such as coma, defocus, and astigmatism, i.e. aberrations that can be represented by varying a single parameter of Zernike polynomials. To go beyond the principled but synthetic setting of primary aberrations, LensCorruptions samples linear combinations in the vector space spanned by Zernike polynomials, corresponding to 100 real lenses. Evaluations for image classification and object detection on ImageNet and MSCOCO show that for a variety of different pre-trained models, the performance on OpticsBench and LensCorruptions varies significantly, indicating the need to consider realistic image corruptions to evaluate a model's robustness against blur.