Code for our paper: "Designing Interpretable Recurrent Neural Networks for Video Reconstruction Via Deep Unfolding" Van Luong, H., Joukovsky, B., & Deligiannis, N. (2021). Designing Interpretable Recurrent Neural Networks for Video Reconstruction via Deep Unfolding. IEEE Transactions on Image Processing, 30, 4099-4113.
OpenHPS is an open source hybrid positioning system written in Typescript. The core component is published as an NPM package under the name @openhps/core.
The code developed allows readers to understand and learn how the speed and separation monitoring algorithm works and how the various variables affect the distances where the robot is slowing down and stopping to prevent any collision. To ease the understanding, we are using constant velocities
Code of our paper: "Interpretable Neural Networks for Video Separation: Deep Unfolding RPCA with Foreground Masking".Contains the ROMAN-S and ROMAN-R models.
The app serves as a comprehensive risk analysis tool, enabling users to gather information about processes, including personal data processing activities, IT, human, and organizational resources. Utilizing the system, users can present information about risks across their organization clearly and transparently.
The Explorotron Visual Studio Code extension is an extension for guided and independent code exploration and learning. The tool is designed to help students learn from arbitrary JavaScript example code they can find by providing different interactive views or so-called study lenses each focusing on different aspects of the code. The individual study lenses are based on computing education research and follow best practices such as the PRIMM methodology, a peel-away design or an environment closely resembling a professional programming environment to support skill transfer.
This is the software associated with the paper "A knowledge graph approach to predict and interpret disease-causing gene interactions|" published in BMC bioinformatics. The code is available via https://github.com/oligogenic/ARBOCK
This package is based on the package TikZ and can be used to draw various kinds of diagrams such as bar charts, doughnut charts, infographics, pie charts, ring charts, square charts, sunburst charts, waffle charts and wheel charts.It provides several options to customize the diagrams. It is also possible to specify a plot for the shape of the chart. Furthermore a legend can be added and the table of contents can be displayed as one of these diagrams.
This package is based on the package TikZ and can be used to draw geometric constructions with liftarms. There are several options for the appearance of the liftarms. It provides an environment to connect multiple liftarms using the Newton-Raphson method and LU decomposition. It also provides an environment to describe a construction and a method to animate a construction with one or more traces.
In this demo, we show an adaptable proof-of-concept web application for a conversational recommender system which supports domain-specific user interface (UI) elements. The application uses a Large Language Model (LLM) for preference elicitation, content-based recommendation, and justification of the outcomes in different explanation styles. Through this interactive example, we aim to highlight three often overlooked aspects in current research on conversational recommender systems: (i) chatbots can go beyond purely text-based interaction patterns by implementing custom UI elements; (ii) function calling is a powerful feature to develop flexible, semi-structured interfaces with LLMs; (iii) due to their general knowledge and RAG extensibility, LLMs can be employed as convincing content-based recommenders to rapidly develop and test interfaces and explanation styles.
DIRESA is a Python package for dimension reduction based on TensorFlow. The distance-regularized Siamese twin autoencoder architecture is designed to preserve distance (ordering) in latent space while capturing the non-linearities in the datasets.PrerequisitesThe DIRESA package depends on the tensorflow and tensorflow_probability packages. These can be installed with the following commands: pip install tensorflow pip install tensorflow_probabilityInstall DIRESAInstall DIRESA with the following command: pip install diresa
Wastrumentation is a dynamic analysis platform for WebAssembly that supports intercession. Wastrumentation is based on source code instrumentation, which weaves the analysis code directly into the target program code. Inlining the analysis into the target’s source code avoids dependencies on the runtime environment, making analyses portable across different Wasm VMs. Wastrumentation's approach enables the implementation of analyses in any Wasm-compatible language.
