Research & Education

d2l-pytorch is an open-source project that meticulously reproduces the content of the acclaimed "Dive Into Deep Learning" book, translating its original MXNet code examples into PyTorch. This adaptation offers students and researchers a valuable resource for understanding and implementing deep learning concepts using the widely adopted PyTorch framework. The repository covers a comprehensive range of topics, from foundational preliminaries like data manipulation and linear algebra to advanced subjects such as convolutional neural networks, recurrent neural networks, attention mechanisms, and various optimization algorithms. It serves as a practical, hands-on guide for learning deep learning through code.

Learn_Machine_Learning_in_3_Months is an open-source GitHub repository offering a structured curriculum for individuals aiming to learn machine learning in three months. Curated by Siraj Raval, this resource provides a week-by-week breakdown of topics, including foundational subjects like linear algebra, calculus, and probability, alongside practical skills such as Python for data science and an introduction to TensorFlow. The curriculum progresses to deep learning concepts, recommending resources like Fast.AI and suggesting project ideas. It serves as a comprehensive guide for self-study, linking to various YouTube playlists, online courses, and additional GitHub repositories.

llm.pdf is a proof-of-concept project showcasing the ability to run an entire Large Language Model (LLM) within a PDF file. This innovative approach leverages Emscripten to compile llama.cpp into asm.js, enabling the LLM to execute directly within the PDF environment through an old PDF JS injection method. The entire LLM file is embedded into the PDF using base64 encoding, allowing for self-contained LLM inference. While currently a proof-of-concept, it highlights the potential for highly portable and self-sufficient AI applications. Users can generate custom PDFs with compatible GGUF quantized models, with 135M parameter models taking approximately 5 seconds per token for input/output.

long-context-attention, also known as Unified Sequence Parallelism (USP) or Hybrid Sequence Parallelism, offers a novel approach to training and inference for long context Large Language Models (LLMs). This open-source project synergizes the strengths of DeepSpeed-Ulysses-Attention and Ring-Attention, addressing their individual limitations. Ulysses-Attention is sensitive to the number of attention heads and less suitable for GQA/MQA scenarios, while Ring-Attention can be less efficient in computation and communication. LongContextAttention provides a more general, versatile, and performant solution. It supports various FlashAttention versions (v2, v3) and can even run without FlashAttention for NPUs. The tool includes functionalities for setting process groups, extracting local tensors, and offers different ring implementation types like 'zigzag' and 'basic'. It has been verified in Megatron-LM and applied in several other projects, providing a robust solution for researchers and developers working with long context generative AI.

Magentic-UI is a research prototype of a human-centered AI agent designed to automate complex web and coding tasks that may require monitoring. Unlike black-box agents, the system reveals its plan before executions, lets users guide its actions, and requests approval for sensitive operations while browsing websites, executing code, and analyzing files. Key features include co-planning for collaborative plan creation, co-tasking for guiding execution, action guards for sensitive operations, and plan learning/retrieval to improve future automation. It supports integration with Microsoft's Fara-7B model and offers flexible configuration for various LLM clients like Azure OpenAI and Ollama, making it a versatile platform for studying human-agent interaction.

LookaheadDecoding is an open-source project designed to significantly accelerate Large Language Model (LLM) inference by breaking the traditional sequential dependency of token generation. This innovative approach utilizes a parallel decoding algorithm, eliminating the need for a draft model or a separate data store. Motivated by Jacobi decoding, LookaheadDecoding collects and caches n-grams from Jacobi iteration trajectories, enabling simultaneous processing of future tokens. The process is divided into a lookahead branch, which generates new n-grams within a defined window, and a verification branch, which validates promising candidates. This method has demonstrated substantial latency reductions, achieving speedups ranging from 1.5x to 2.3x on various datasets and models. The tool supports sampling and FlashAttention, and is implemented with an attention mask to maximize GPU parallel computing power, making it a valuable resource for optimizing LLM performance.

Data-science-on-aws is an open-source resource designed to educate users on implementing AI and Machine Learning solutions within the Amazon Web Services (AWS) ecosystem. It provides comprehensive examples for constructing end-to-end AI/ML pipelines, leveraging powerful tools such as Kubeflow, Amazon EKS, and Amazon SageMaker. The resource is structured around an O'Reilly book, offering practical, hands-on demonstrations. Users will learn to train and tune BERT models for natural language processing, perform hyper-parameter tuning, A/B testing, and set up real-time streaming analytics. It covers data ingestion, exploration, preparation, model training, optimization, deployment, and security, making it ideal for those looking to master data science workflows on AWS.

Matterport3DSimulator is an AI research platform designed for deep reinforcement learning, computer vision, natural language processing, and robotics. It allows AI agents to interact with real 3D environments using visual information derived from panoramic RGB-D images. The simulator is based on the Matterport3D dataset, featuring 90 diverse indoor environments. Key capabilities include outputting real RGB and depth images, customizable image resolution and camera parameters, and support for off-screen rendering. It offers both C++ and Python APIs and is highly efficient, capable of around 1000 fps RGB-D off-screen rendering. The platform also includes the Room-to-Room (R2R) navigation dataset and task for training agents to follow natural language instructions.

Data-Science-45min-Intros is a GitHub repository offering a collection of IPython notebook presentations designed for quick, 45-minute learning sessions. Originating from the data science team at Gnip (TwitterBoulder), these resources cover fundamental programming concepts, statistical methods, and machine learning techniques. Topics range from Python object-oriented programming and unit testing to advanced machine learning algorithms like K-means, Naive Bayes, and neural networks. It also includes content on natural language processing, network analysis, data visualization with D3 and Bokeh, and database interactions with SQL and Vertica. The project encourages community contributions via pull requests, making it a collaborative learning resource.

Data-Science-and-Machine-Learning-Projects-Dojo is an open-source GitHub repository offering a comprehensive collection of data science, machine learning, deep learning, and data visualization projects. It serves as a practical dojo for individuals to practice and enhance their skills in these areas, covering theories, probability, and statistics. The projects utilize popular libraries such as NumPy, Pandas, Scikit-learn, TensorFlow, Keras, NLTK, Matplotlib, Seaborn, and Plotly. It also includes examples of turning ML models into web applications using Streamlit and Flask, and explores Apache Spark for large-scale data processing. The repository features diverse projects like breast cancer tumor diagnostics, movie rating analysis, customer churn prediction, heart disease prediction, bulldozer sale price prediction, and dog breed classification.

data-science-learning-resources is a comprehensive collection of curated learning materials for data science and machine learning. The repository, maintained by Bradley Boehmke, focuses on resources that the creator has personally read and found helpful, ensuring a high level of quality and relevance. It categorizes resources into key areas such as Programming (Python, R, Spark, Command Line, Containers, Functional Programming, Version Control, Code Packaging, Style Guide, Testing), Machine Learning (General, Unsupervised Modeling, A/B Testing, various algorithms like MARS, KNN, Random Forests, GBM, Deep Learning, Ensembles, NLP, Recommendation Systems, Tuning, Feature Engineering, Interpretability, AutoML, Benchmarking, Resampling, Productionalization, Model Monitoring), and Leadership & Strategy (Management & Leadership, Cloud Strategy, Product, Performance Reviews). This makes it an invaluable resource for anyone looking to deepen their understanding and skills in these domains.

Kibo by Trestle Labs is an AI-powered solution designed to make content digitally inclusive for individuals, libraries, NGOs, and corporations. It transforms printed, handwritten, scanned, and digital content into accessible formats, including searchable PDFs, editable documents, and MP3 audiobooks. Kibo supports listening, translating across 100+ languages, digitizing, and audiotizing content. The platform offers various kits like Kibo 2.0, Kibo XS, and Kibo 360 for different use cases, along with AI APIs for embedding its capabilities. It also provides mobile and web applications, empowering over 100,000 people, particularly those with visual impairments, by offering subsidies through partnerships like VOSAP.

The Saarland Informatics Campus (SIC) is a prominent center for computer science education and research in Europe, located in Saarbrücken, Germany. It brings together the Universität des Saarlandes with its three interconnected departments and four internationally recognized research institutes, covering the entire spectrum of informatics. SIC offers 24 diverse study programs, including Bachelor's and Master's degrees in fields like Computer Science, Bioinformatics, Cybersecurity, and Artificial Intelligence. With over 1000 scientists and 2600 students from 81 nations, it fosters an international and dynamic academic environment. The campus is dedicated to training future leaders in both industry and academia, emphasizing innovation, interdisciplinary collaboration, and a strong connection between fundamental research and practical applications.

machine-learning-surveys is a comprehensive GitHub repository offering a curated list of surveys, tutorials, and books related to machine learning. This resource is organized by topic, making it easy for users to find relevant literature on areas such as Active Learning, Bioinformatics, Classification, Clustering, Computer Vision, Deep Learning, Natural Language Processing, Reinforcement Learning, and more. Each entry typically includes the title, authors, and page count, with some entries highlighted for their significance. It serves as an excellent starting point for students, researchers, and professionals looking to deepen their understanding or explore specific subfields within machine learning.

MedMNIST is a comprehensive collection of 18 standardized biomedical image datasets, designed for 2D and 3D classification tasks. It includes 12 datasets for 2D images and 6 for 3D images, with various size options such as MNIST-like 28x28, and larger 64x64, 128x128, and 224x224 for 2D, plus 64x64x64 for 3D. These datasets cover diverse data modalities, scales (from 100 to 100,000 samples), and tasks (binary/multi-class, ordinal regression, multi-label). MedMNIST aims to simplify biomedical image analysis for researchers by providing pre-processed data and standardized train-validation-test splits, making it user-friendly for machine learning algorithm development and comparison. It is particularly useful for educational purposes due to its accessibility and lack of prerequisite background knowledge.

BIFOLD, the Berlin Institute for the Foundations of Learning and Data, conducts groundbreaking foundational research in Big Data Management (DM) and Machine Learning (ML), as well as their intersection. The institute is dedicated to educating future talents and generating high-impact knowledge in these critical fields. BIFOLD actively engages in various research projects, publishes scientific papers, and contributes to open-source systems, tools, and data. It fosters collaboration among researchers, policymakers, and industry representatives, as evidenced by events like BIFOLD Day. The institute also offers a Graduate School with innovative PhD programs for both bachelor's and master's degree holders, aiming to advance the next generation of AI and data science experts.

The live website content for SapienAPI is entirely in Chinese and primarily displays information related to industrial equipment, such as various types of saws, cutting machines, and related accessories. There is no discernible information or mention of AI, search engines, or any related technology. The meta tags and homepage content are also in Chinese, focusing on industrial products and contact information for a company in Shijiazhuang. The original description of SapienAPI as an AI-powered search tool utilizing LLMs and real-time web data to find websites is not supported by the current live website content.

Deep-Learning-with-Keras is an open-source code repository published by Packt, serving as a companion to the book 'Deep Learning with Keras'. It offers all the necessary project files to follow along with the book's content, from introductory concepts to advanced deep learning techniques. The repository covers supervised learning algorithms like linear regression, multilayer perceptrons, and Deep Convolutional Networks, as well as unsupervised learning algorithms such as Autoencoders, Restricted Boltzmann Machines, and Deep Belief Networks. It also delves into Recurrent Networks and Long Short Term Memory (LSTM) networks. Users can explore image processing tasks, including handwritten digit recognition, image classification, and object recognition with annotations, alongside an example of salient point identification for face detection. The code is organized into chapters, requiring software like TensorFlow, Keras, Matplotlib, Scikit-learn, and NumPy.

deep-learning-wizard offers open-source guides and code for mastering deep learning, from foundational concepts to production deployment. The resource covers a wide array of topics including machine learning, deep learning, deep reinforcement learning, data engineering, and general programming. It provides tutorials on PyTorch, Python, Apptainer, and other relevant libraries, making it suitable for both beginners and those looking to deepen their expertise. The platform is designed to be mobile and tablet-friendly, ensuring accessibility for learners on various devices. It also includes sections on language models, HPC containers, and optimization techniques, aiming to provide a comprehensive learning experience for deep learning practitioners.

WERULE is an award-winning AI-powered mentorship community and app specifically designed for female founders and entrepreneurs. Recognized by the United Nations, it provides a white-label mentorship platform that helps organizations scale their mentorship programs, enhance leadership skills, and measure the impact of these initiatives through advanced data insights. The platform features a community of entrepreneurs, innovators, and change-makers, offering access to expert mentors for booking sessions. WERULE also offers resources like 'The Founder Archive' blog, which provides actionable blueprints on leadership, mentorship, and career building, deconstructing success stories from various innovators.

DeepTutor is an agent-native personalized learning assistant designed to enhance the educational experience through adaptive and intelligent tutoring. It features a unified chat workspace with six modes, including Deep Solve, Quiz Generation, Deep Research, Math Animator, and Visualize, all sharing the same context. The AI Co-Writer acts as a first-class collaborator in a multi-document Markdown workspace, drawing from your knowledge base and the web to rewrite, expand, or summarize text. Its Book Engine compiles structured, interactive "living books" with 14 block types, such as quizzes, flashcards, and interactive demos. DeepTutor also includes a Knowledge Hub for building RAG-ready knowledge bases from various document types and persistent memory that builds a living profile of the user's learning journey. Personal TutorBots offer autonomous tutoring with their own memory, personality, and skill sets, evolving with the user.

ClozeGPT leverages artificial intelligence to generate custom cloze text exercises, specifically designed to aid in language acquisition. The tool offers personalized learning paths and adaptable study materials, catering to diverse user needs and learning styles. By focusing on interactive and tailored content, ClozeGPT aims to enhance vocabulary and comprehension effectively. It provides a targeted approach to language learning, allowing users to practice and reinforce their understanding through engaging cloze activities.

R Discovery is an AI-powered platform designed to streamline academic research for students and researchers. It offers access to over 300 million research papers, including 40 million open-access articles, across 32,000 journals. Users receive personalized reading feeds based on their interests, ensuring they stay updated with the latest and most relevant academic research. Key features include an AI assistant for summaries and paper references, a Chat PDF tool for interactive questioning, and a literature review generator. The platform also supports audio papers, paper translations into 30+ languages, and institutional access to paywalled articles, making academic research reading a more efficient and accessible experience.

DeepLearning_tutorials is an open-source repository offering a collection of deep learning algorithms meticulously implemented using TensorFlow. It serves as a valuable resource for students, researchers, and developers looking to understand and practice various neural network architectures. The repository includes implementations of fundamental algorithms like Logistic Regression, Multi-Layer Perceptron (MLP), Convolutional Neural Networks (CNN), Denoising Autoencoders (DA), Stacked Denoising Autoencoders (SDA), Restricted Boltzmann Machines (RBM), and Deep Belief Networks (DBN). Additionally, it features popular CNN models such as MobileNet, ResNet, and DenseNet, alongside object detection algorithms like YOLOv1, SSD, and YOLOv2. Practical examples cover applications like CNN for sentence classification, RNN/LSTM for language models, and GAN/VAE for generative tasks, all within the TensorFlow framework.