Research & Education

Giotto-tda is a high-performance topological machine learning toolbox implemented in Python, designed to facilitate advanced data analysis and machine learning research. Built on top of the scikit-learn ecosystem, it offers robust algorithms for topological data analysis (TDA). The toolbox is part of the Giotto family of open-source projects and is distributed under the GNU AGPLv3 license. It supports Python 3.7+ and integrates with popular libraries like NumPy, SciPy, and Plotly. Giotto-tda is the result of a collaborative effort between L2F SA, EPFL, and HEIG-VD, making it a reliable tool for researchers and data scientists working with complex datasets.

The Institute for Computational Mechanics (Wall Lab) at the Technical University of Munich (TUM) is dedicated to cutting-edge research in computational mechanics. Their work spans application-motivated fundamental research, with a particular emphasis on complex coupled multifield and multiscale problems across various engineering and applied science domains. The institute's activities encompass advanced modeling techniques, the development of novel computational methods, and the creation of specialized software for high-performance computing systems. This focus enables them to tackle challenging scientific and engineering questions, contributing to advancements in fields requiring sophisticated simulation and analysis.

InterpretableMLBook is the Chinese translation of "Interpretable Machine Learning" by Christoph Molnar, a highly regarded work in the field of interpretable machine learning. This book serves as a comprehensive guide to understanding the interpretability of black-box models, making complex concepts accessible to a Chinese-speaking audience. It systematically organizes interpretability methods, describing each through intuitive language and detailed mathematical formulas. A key feature is the practical application of each method to real-world data, allowing readers to truly grasp their utility. The book also includes critical discussions on the advantages and disadvantages of various methods, making it a valuable resource for both technical practitioners and researchers.

The LangChain-Chinese-Getting-Started-Guide is an open-source tutorial designed to help Chinese speakers learn and utilize the powerful LangChain framework. It covers essential concepts such as LLM invocation, prompt management, document loaders, text splitters, vector stores, chains, and agents. The guide provides practical examples, including performing Q&A with OpenAI models, integrating with Serpapi for internet searches, and summarizing long texts. It also addresses common challenges like API token limits and offers solutions using LangChain's features. The tutorial is actively maintained on GitHub, with updates and code examples available for hands-on learning.

KB2E is a knowledge graph embedding tool developed as a subproject of THU-OpenSK. It provides implementations for several prominent knowledge graph embedding algorithms, including TransE, TransH, TransR, and PTransE. These algorithms are crucial for representing entities and relations in a knowledge graph as low-dimensional vectors, enabling various downstream tasks like link prediction and entity classification. While the project offers valuable resources for researchers and developers interested in knowledge graph embeddings, it is important to note that KB2E is no longer actively maintained. Users are advised to transition to the newer and actively supported OpenKE package for continued development and support in this domain.

Machine-learning-engineering-for-production-public serves as the official public repository for DeepLearning.AI's Machine Learning Engineering for Production Specialization. This resource is designed to support students and professionals in understanding the intricacies of deploying machine learning models into real-world production environments. The repository contains various materials, including course content, labs, and other public resources relevant to the specialization's curriculum. While it provides valuable learning assets, the repository is currently not accepting pull requests for contributions. It is an essential companion for anyone undertaking the DeepLearning.AI MLEP Specialization, offering practical insights and foundational knowledge for machine learning engineering.

Machine-Learning-Interviews is an open-source GitHub repository designed to guide individuals through the preparation process for Machine Learning and AI technical interviews. This resource is particularly valuable for those targeting roles like Machine Learning Engineer and Applied Scientist at prominent tech companies. It covers essential interview modules such as general coding (algorithms and data structures), ML-specific coding, ML fundamentals, ML system design, and behavioral questions. The repository also includes a new section on Agentic AI Systems, reflecting the latest trends in AI engineering. Compiled from the author's personal experience and successful interview preparations, it offers a structured approach to mastering the diverse components of technical ML interviews.

machine-learning-yearning-cn is the Chinese translation of Andrew Ng's influential book, "Machine Learning Yearning." This resource is specifically designed to equip AI engineers and practitioners with practical, technical strategies for navigating the complexities of machine learning projects. It covers essential topics related to training and managing machine learning systems, offering insights into debugging, error analysis, and overall project optimization. The project is open-source and encourages community contributions to improve translation quality, making it a collaborative effort to disseminate crucial AI knowledge within the Chinese-speaking community. It serves as a valuable study assistant for those looking to deepen their understanding and application of machine learning principles.

named_entity_recognition is an open-source project dedicated to Chinese named entity recognition (NER), offering practical implementations of several prominent models. It includes Hidden Markov Model (HMM), Conditional Random Field (CRF), Bi-directional Long Short-Term Memory (BiLSTM), and a hybrid BiLSTM+CRF model. The project utilizes a resume dataset for training and evaluation, providing detailed accuracy, recall, and F1 scores for each model. It serves as a valuable resource for researchers and developers interested in NLP, particularly in the context of Chinese NER, allowing for direct comparison and understanding of different algorithmic approaches.

pml2-book, or "Probabilistic Machine Learning: Advanced Topics," is a comprehensive book authored by Kevin Murphy, focusing on advanced concepts within probabilistic machine learning. This resource is openly available as a PDF, primarily distributed through its GitHub repository, allowing for easy access and tracking of downloads and issues. It is designed for individuals who already possess a foundational understanding of machine learning and are looking to delve into more complex and specialized areas. The repository also includes various supplementary materials such as prefaces and tables of contents, offering a detailed overview of the book's structure and content.

MiVOLO-Demo is an AI-powered tool available on Hugging Face Spaces that allows users to upload an image and receive an estimation of the age and gender of individuals within it. The platform provides options to adjust detection settings, which can help improve the accuracy of the results. Developed by Irina Tolstykh, this web application falls under the AIApplication category and is licensed under Apache 2.0. It offers a straightforward interface for exploring AI capabilities in facial analysis, making it accessible for quick demonstrations and personal use.

PyHealth is a comprehensive, open-source deep learning Python toolkit designed to support clinical predictive modeling for both ML researchers and medical practitioners. It aims to make healthcare AI applications easier to develop, test, and deploy, offering flexibility and customizability. Key features include a modular 5-stage pipeline, a healthcare-first approach with support for medical codes and clinical datasets like MIMIC and eICU, and over 33 pre-built models with production-ready trainers and metrics. The toolkit supports more than 10 healthcare tasks and datasets, providing fast data processing for quick experimentation. PyHealth also includes independent modules for medical code mapping (pyhealth.medcode) and medical code tokenization (pyhealth.tokenizer), enhancing its utility for complex healthcare data.

Thinking_in_Java_MindMapping is an open-source GitHub repository that serves as a comprehensive collection of programming notes, AI learning resources, and personal insights. Initially focused on Java mind maps, the project has expanded to include detailed notes on Java, Redis, Spring, algorithms, and AI agents. Beyond technical content, it features reading notes, movie guides, and game records, making it a diverse knowledge base. The repository is actively maintained with automated navigation updates, ensuring easy access to its wide array of content, from in-depth Java analyses to AI principles and personal reflections.

machine_learning_with_python_jadi is an open-source GitHub repository offering a collection of Jupyter notebooks specifically designed for a machine learning course. The repository includes various practical examples covering topics such as classification (Decision Trees, K-Nearest Neighbors, Logistic Regression, SVM), clustering (DBSCAN, Hierarchical, K-Means), regression (Linear, Non-Linear, Polynomial), and recommender systems (Collaborative and Content-Based Filtering). It also provides several datasets like ChurnData.csv, FuelConsumption.csv, and movies.csv, which are used within the notebooks for hands-on exercises. This resource is ideal for students and developers looking to learn and practice machine learning concepts using Python.

Book7_Visualizations-for-Machine-Learning is an open-source GitHub repository offering a comprehensive educational resource for machine learning. It provides Python code examples for various machine learning algorithms, alongside detailed PDF explanations. The content covers a wide range of topics, from regression analysis and regularization to clustering and dimensionality reduction techniques. Designed to help users understand complex machine learning concepts through practical visualizations, this resource is particularly valuable for students and enthusiasts. The materials are primarily in Chinese, making it a significant resource for Chinese-speaking learners.

Braindecode is an open-source Python toolbox specifically designed for decoding raw electrophysiological brain data using deep learning models. It offers a comprehensive suite of functionalities, including dataset fetchers, robust data preprocessing tools, and visualization capabilities. The toolbox also features implementations of various deep learning architectures and data augmentations, making it suitable for in-depth analysis of EEG, ECoG, and MEG signals. It caters to both neuroscientists interested in applying deep learning and deep learning researchers looking to work with neurophysiological data, providing a powerful platform for advanced brain signal analysis.

Real-time-ML-Project is an open-source repository offering a curated list of applied machine learning and data science notebooks and libraries across diverse industries. Primarily utilizing Python and Jupyter notebooks, this resource is designed to assist analytical, computational, statistical, and quantitative researchers, as well as machine learning engineers and data scientists. It covers a wide array of sectors including Accommodation & Food, Agriculture, Banking & Insurance, Healthcare, and Manufacturing, providing practical examples and code for various applications. Users are encouraged to contribute their own tools and notebooks, making it a collaborative and evolving platform for real-world ML solutions.

AI Matters EU is a Testing and Experimentation Facility (TEF) dedicated to validating new AI and robotics technologies within the manufacturing sector. The initiative aims to increase the flexibility of European manufacturing industries by deploying advanced AI solutions. It provides access to state-of-the-art facilities and real-world manufacturing data, enabling companies to test and mature their AI solutions. Services include XR-based training tools for industrial activities, XR-based digital twin simulations of assembly lines, XAI consulting, and workshops on vision technologies. Companies established in Europe can access these services, potentially with financial aid, to integrate and test their solutions in a real-world context. The project is a collaborative effort involving 22 partners across 8 European countries, bringing together expertise in various manufacturing sectors.

DictionaryByGPT4 is an AI-generated English vocabulary resource created using GPT-4, offering comprehensive analysis for over 8000 words. Each entry includes detailed definitions, multiple example sentences, in-depth etymology (root and affix analysis), cultural background, word transformations (nouns, verbs, adjectives, tenses), memory techniques, and short illustrative stories. This tool aims to enhance language learning by providing a rich, contextual understanding of words, moving beyond rote memorization. It is available in various formats including EPUB, PDF, online web pages, JSON data, and an MDX dictionary, making it accessible for diverse learning preferences.

Learna is an AI-powered English tutor developed by Codeway, designed to make language learning personal, fun, and effective. It speaks, listens, and adapts like a human teacher, utilizing advanced technologies such as talking head tech, Gaussian image generation, and natural language understanding. With over 15 million downloads and a 4.5 rating, Learna offers an engaging and interactive way for users to improve their English proficiency through AI-driven conversations and adaptive learning experiences. It is available on both Google Play and the App Store.

CourseraML is an open-source project that re-implements Andrew Ng's Machine Learning course assignments from Coursera using Python and Jupyter notebooks. This tool serves as a valuable resource for individuals looking to deepen their understanding of machine learning through hands-on practice. By providing the assignments in a Python-native, interactive notebook format, CourseraML caters to those who prefer working within the Jupyter ecosystem. It offers a practical, code-centric approach to learning core machine learning concepts, making it an excellent supplementary resource for students, researchers, and self-learners in the field.

Illustrated Machine Learning is a website dedicated to simplifying complex Machine Learning concepts through clear and concise illustrations. It aims to provide a visual learning resource for a diverse audience, including students, professionals, and individuals preparing for technical interviews. The platform focuses on making the underlying theories of Machine Learning more accessible and easier to understand, serving as a valuable aid for both beginners and seasoned professionals looking to refresh their knowledge. The website encourages community involvement, inviting users to report any mistakes and contribute to its development, fostering a collaborative learning environment.

ebookMLCB is an open-source ebook focused on fundamental machine learning concepts, authored by Vũ Hữu Tiệp. Available as a PDF, it serves as an educational resource for individuals interested in studying machine learning. The project is hosted on GitHub, providing access to the source code and allowing for community contributions. Users can download both black-and-white and color versions of the ebook. While the physical book is no longer sold, the digital version remains accessible. The author requests proper attribution for any sharing and requires consent for copying or printing, emphasizing its educational and non-commercial intent.

GROBID (Generation Of BIbliographic Data) is an open-source machine learning library designed to extract, parse, and restructure raw PDF documents, particularly technical and scientific publications, into structured XML/TEI encoded formats. Developed since 2008, it offers functionalities like header extraction (title, abstract, authors), reference parsing (with high F1-scores), citation context recognition, and full-text structuring (sections, figures, tables). GROBID also provides PDF coordinates for interactive augmented PDFs, name and affiliation parsing, and consolidation of references using services like biblio-glutton or CrossRef. It includes a comprehensive web service API, Docker images, and supports batch processing, making it suitable for large-scale scientific literature processing. Deployments include ResearchGate, Semantic Scholar, and HAL Research Archive.