Related papers: Paraconsistent-Lib: an intuitive PAL2v algorithm P…
In this work, we tackle the problems of efficiency and scalability for predictive coding networks (PCNs) in machine learning. To do so, we propose a library, called PCX, that focuses on performance and simplicity, and use it to implement a…
This paper introduces the first, open source software library for Constraint Consistent Learning (CCL). It implements a family of data-driven methods that are capable of (i) learning state-independent and -dependent constraints, (ii)…
As computational challenges in optimization and statistical inference grow ever harder, algorithms that utilize derivatives are becoming increasingly more important. The implementation of the derivatives that make these algorithms so…
We introduce EvoLib, a test-time learning framework that enables large language models to accumulate, reuse, and evolve knowledge across problem instances without parameter updates or external supervision. Instead of adapting model…
This paper introduces HyperNOs, a PyTorch library designed to streamline and automate the process of exploring neural operators, with a special focus on hyperparameter optimization for comprehensive and exhaustive exploration. Indeed,…
Pylearn2 is a machine learning research library. This does not just mean that it is a collection of machine learning algorithms that share a common API; it means that it has been designed for flexibility and extensibility in order to…
We present panco2, an open-source Python library designed to extract galaxy cluster pressure profiles from maps of the thermal Sunyaev-Zeldovich effect. The extraction is based on forward modeling of the total observed signal, allowing to…
Selecting a library out of numerous candidates can be a laborious and resource-intensive task. We present the $crypto_{lib}$ index, a tool for decision-makers to choose the best fitting cryptography library for a given context. To define…
Signature-based methods have recently gained significant traction in machine learning for sequential data. In particular, signature kernels have emerged as powerful discriminators and training losses for generative models on time-series,…
PARAGEN is a PyTorch-based NLP toolkit for further development on parallel generation. PARAGEN provides thirteen types of customizable plugins, helping users to experiment quickly with novel ideas across model architectures, optimization,…
PyCPL provides full access to ESO's Common Pipeline Library ( CPL) for astronomical data reduction within a Python environment. Not only does it offer a Python interface to the robust CPL library, but it also lets users and developers fully…
Python is one of the most commonly used programming languages in industry and education. Its English keywords and built-in functions/modules allow it to come close to pseudo-code in terms of its readability and ease of writing. However,…
An algorithm implemented in an open-source python library was developed for building periodic coincidence site lattice (CSL) grain boundary models in a universal fashion. The software framework aims to generate tilt and twist grain…
Laboratory tests play a major role in clinical decision making because they are essential for the confirmation of diagnostics suspicions and influence medical decisions. The number of different laboratory tests available to physicians in…
Mean-field games (MFGs) are limiting models to approximate $N$-player games, with a number of applications. Despite the ever-growing numerical literature on computation of MFGs, there is no library that allows researchers and practitioners…
Network alignment (NA) aims to identify node correspondence across different networks and serves as a critical cornerstone behind various downstream multi-network learning tasks. Despite growing research in NA, there lacks a comprehensive…
The growing popularity of generative flow networks (GFlowNets or GFNs) from a range of researchers with diverse backgrounds and areas of expertise necessitates a library that facilitates the testing of new features (e.g., training losses…
This paper introduces pyRDF2Vec, a Python software package that reimplements the well-known RDF2Vec algorithm along with several of its extensions. By making the algorithm available in the most popular data science language, and by bundling…
We present an open source Python 3 library aimed at practitioners of molecular simulation, especially Monte Carlo simulation. The aims of the library are to facilitate the generation of simulation data for a wide range of problems; and to…
Path signatures provide a rich representation of sequential data, with strong theoretical guarantees and good performance in a variety of machine-learning tasks. While signatures have progressed from fixed feature extractors to trainable…