Research & Education

Mallet is an open-source, Java-based package designed for statistical natural language processing and machine learning applications to text. It provides sophisticated tools for document classification, including efficient text-to-feature conversion, various algorithms like Naïve Bayes and Maximum Entropy, and performance evaluation metrics. Beyond classification, Mallet supports sequence tagging for tasks such as named-entity extraction using algorithms like Hidden Markov Models and Conditional Random Fields. Its topic modeling toolkit offers efficient, sampling-based implementations of Latent Dirichlet Allocation and Hierarchical LDA. The package also includes routines for transforming text documents into numerical representations through a flexible system of "pipes" for tokenizing, stopword removal, and count vector conversion. Mallet is ideal for researchers and practitioners working with large text datasets.

DGL-LifeSci is an open-source Python package built on DGL (Deep Graph Library) specifically designed for deep learning applications in life sciences using graph neural networks. It provides a comprehensive suite of tools for researchers and developers, including methods for constructing and featurizing molecular graphs and biological networks, evaluating models, and offering various model architectures. The package also includes training scripts and pre-trained models to accelerate research and development. DGL-LifeSci supports applications such as molecular property prediction and reaction prediction, making it a valuable resource for advancing drug discovery and bioinformatics.

DIG (Dive into Graphs) is a comprehensive open-source library designed for graph deep learning research. Unlike basic graph deep learning libraries, DIG offers a unified testbed for advanced, research-oriented tasks such as graph generation, self-supervised learning on graphs, explainability of Graph Neural Networks, deep learning on 3D graphs, and graph out-of-distribution. It provides unified implementations of data interfaces, common algorithms, and evaluation metrics, allowing researchers to easily implement their own methods and compare them against baseline methods using common datasets and metrics without extensive effort. The library supports various research directions including Graph Augmentation and Fair Graph Learning, and is built on PyTorch Geometric (PyG).

DeepLearningFlappyBird is an open-source project that showcases the application of Deep Reinforcement Learning, specifically Deep Q-learning, to train an AI agent to play the game Flappy Bird. This project is based on the Deep Q Learning algorithm described in "Playing Atari with Deep Reinforcement Learning" and generalizes it to the Flappy Bird environment. It provides a practical, hands-on example for individuals interested in understanding and implementing deep learning algorithms within game environments. The project details the installation process, the architecture of the convolutional neural network used, and the training methodology, including preprocessing steps and hyperparameter annealing. It is an excellent resource for educational purposes and experimentation with AI.

DeepLearningPython is a GitHub repository that offers updated scripts from neuralnetworksanddeeplearning.com, specifically tailored for Python 3.5.2 and integrated with the Theano deep learning library, including CUDA support. This resource provides a practical foundation for individuals looking to learn and implement neural networks. The repository includes three distinct network implementations (network.py, network2.py, network3.py) from the original book, all runnable via a single testing file, test.py. This setup allows users to easily train and evaluate different network configurations, with examples and comments linking back to specific chapters of the book. It's an excellent tool for hands-on learning and experimentation in deep learning.

DeepLearningVideoGames is a project focused on applying deep Q-networks to develop AI agents capable of learning optimal control patterns from visual input in video games. Utilizing reinforcement learning, specifically Q-learning with convolutional neural networks, the system processes raw pixel values from game screens to approximate future expected rewards for actions. The project successfully trained an AI to achieve better than human performance in Pong and is actively working on Tetris. It highlights the potential of deep learning for generalizable high-level control schemes in gaming, demonstrating how AI can learn complex strategies without explicit knowledge of game rules.

Data-Science-Roadmap is an open-source repository designed to guide individuals through a comprehensive self-learning journey in data science. It meticulously outlines a roadmap from foundational concepts to advanced topics, including programming languages like Python and R, statistical analysis, machine learning, and deep learning. The roadmap is structured into beginner, intermediate, and advanced phases, each providing a curated list of free resources such as videos, online articles, and books. It emphasizes practical skills like data cleaning, visualization, and SQL, and offers guidance on preparing a workspace and avoiding common learning pitfalls. This tool is ideal for anyone looking to break into the data science field without financial barriers, offering a structured path and valuable learning materials.

deep-learning-v2-pytorch is a comprehensive repository offering projects and exercises for Udacity's Deep Learning Nanodegree program. It features a collection of tutorial notebooks covering diverse deep learning topics, guiding users through the implementation of models such as convolutional networks, recurrent networks, and Generative Adversarial Networks (GANs). The resource also delves into other essential concepts like weight initialization and batch normalization. Beyond tutorials, it provides starting code for Nanodegree projects, which are typically reviewed by Udacity reviewers. This repository is ideal for students and learners looking to gain practical experience and deepen their understanding of deep learning with PyTorch.

CENTURY Tech is an AI-powered online learning platform designed to personalize education in English, maths, and science for primary, secondary, and further education. Trusted by schools and colleges globally, it leverages learning science, AI, and neuroscience to adapt to individual student needs. The platform offers personalized learning paths, thousands of learning videos, and self-marking questions, aiming to increase student attainment and progress. It also reduces teacher workload by automating marking, analysis, and resource creation, providing actionable data insights for timely interventions. CENTURY Tech supports various educational contexts, including home learning, entrance exam preparation, and professional development for educators.

deep_learning_curriculum offers an advanced, open-source curriculum designed for individuals seeking to understand the latest developments in deep learning, with a particular emphasis on large language model alignment. It is hosted on GitHub and is intended for those with a strong quantitative background who are already familiar with the fundamentals of deep learning. The curriculum is structured into nine chapters covering topics like Transformers, Scaling Laws, Optimization, Reinforcement Learning, and Alignment. Each chapter includes recommended reading, optional reading, and suggested exercises to facilitate hands-on learning. While challenging, it provides a comprehensive pathway for self-study or mentored learning in this rapidly evolving field.

ChatGPT Continuer is a Chrome extension designed to improve the user experience with ChatGPT by automating the "Continue Generating" button. When ChatGPT's responses stop mid-sentence, this tool automatically clicks the button, allowing the conversation to flow seamlessly without requiring manual intervention. This eliminates the frustration of interrupted responses and ensures a more enjoyable and efficient interaction with the AI. It's particularly useful for users who engage in long conversations or generate extensive content, as it prevents the need to constantly monitor and click to continue the output. The developer has stated that it does not collect or use user data, prioritizing privacy.

AnkiDecks is an AI learning platform designed to rapidly generate Anki flashcards from diverse sources such as PDF, PowerPoint, Word, Epub files, text, and even YouTube links. This tool significantly reduces the time users spend creating flashcards, allowing them to concentrate more on studying. It is particularly beneficial for medical students and language learners, offering features like automatic image occlusion, support for over 50 languages, and various flashcard types including Question-Answer, Cloze, Multiple Choice, and Image Occlusion. Users can export generated flashcards to the Anki app or study them directly on the AnkiDecks platform using its integrated FSRS algorithm.

Made With ML by Anyscale provides comprehensive courses and resources for individuals looking to master the entire lifecycle of production machine learning applications. The platform covers essential topics from design and data handling to model training, deployment, and iteration. It emphasizes best practices in software engineering for ML, scalability, MLOps integration, and CI/CD workflows. The content is designed for a diverse audience, including software engineers, data scientists, college graduates, and product/leadership roles, aiming to bridge the gap between academic knowledge and industry expectations. The curriculum focuses on first principles, practical skills, and scaling ML workloads in Python, ensuring learners can confidently go from development to production.

MOSS-Speech Demo is an innovative speech-to-speech language model developed by the OpenMOSS-Team, available as a Hugging Face Space. This application enables users to input any text and receive an audio output spoken in a clear, human-like voice. The system generates an audio file that can be played directly or downloaded for later use. It is designed for experimenting with true speech-to-speech translation, making it suitable for research and development in multilingual communication. The tool provides a straightforward interface for quick text-to-speech conversion.

Intology is a research lab based in San Francisco dedicated to automating the process of scientific discovery. They develop end-to-end automated research systems, which they refer to as "Artificial Scientists." These systems have demonstrated significant capabilities, including publishing fully AI-generated A* conference papers and outperforming human experts in AI research and development tasks. Intology's core mission is to advance AI research through sophisticated automation, pushing the boundaries of what artificial intelligence can achieve in scientific exploration and discovery.

Multilingual Accessible Mistral 7B is an AI chatbot designed to facilitate multilingual communication. This tool is particularly useful for individuals engaged in language learning, offering a platform to practice and interact in various languages. Beyond language acquisition, it also serves as a valuable resource for content generation, allowing users to create text in multiple languages. The tool is accessible for free, making it an ideal choice for educational purposes and for those interested in exploring the capabilities of AI models without financial commitment. Its focus on accessibility and multilingual support positions it as a versatile tool for a diverse user base.

Hello-AI is an intelligent, AI-driven navigation hub designed to help developers and enthusiasts navigate the vast and rapidly evolving landscape of open-source AI projects. Unlike traditional, manually maintained directories, Hello-AI utilizes AI agents for continuous, autonomous discovery, quality assessment, and categorization of projects. It offers an evolutionary landscape map covering foundational models, Agent frameworks, RAG, infrastructure, multimodal apps, and developer tools, ensuring precise and intuitive organization. The system dynamically tracks project activity, purging stale entries and updating metrics like Star counts to present only the most relevant and active repositories. Additionally, AI automatically generates concise summaries and use-cases for each project, enabling users to quickly identify suitable tools without extensive manual research. The project is open-source and can be deployed locally, offering a hands-free, continuous discovery pipeline.

Netangular is an AI research and deployment company dedicated to advancing artificial intelligence technology. The company emphasizes safety and practical utility in its development process, aiming to create AI solutions that are both effective and responsible. Netangular values diverse perspectives and experiences, striving to make AI accessible and beneficial for addressing meaningful challenges across various domains. Their core mission revolves around building AI responsibly, ensuring that their innovations contribute positively to society while maintaining high standards of ethical development and deployment. The company's focus is on foundational AI research and its application to real-world problems.

Musicgen Songstarter Demo is an AI-powered tool hosted on Hugging Face Spaces, designed to help users quickly generate musical ideas. By providing a text description of the desired music, including genre, instruments, and tempo, the tool creates a 30-second stereo audio track. An optional feature allows users to upload a short melody, which the AI then uses as a guide to influence the generated output. This makes it an accessible platform for experimenting with different musical styles and overcoming creative blocks, providing a rapid prototyping solution for musicians and content creators.

NeuralJam is a digital learning community designed to foster collaboration and turn knowledge into intelligence. It offers an AI-powered personality assessment tool to help users understand themselves and design personalized learning paths. The platform provides a wide range of interactive learning activities, insightful content, and opportunities to connect with like-minded individuals through groups and shared experiences. Users can track their progress, discover new ideas through a daily feed, and access a library of articles, podcasts, and videos. NeuralJam aims to make learning accessible and supports a mission of continuous improvement through collective intelligence, operating without advertising or misuse of personal data.

Grokking-Deep-Learning is a GitHub repository that serves as a companion to the book "Grokking Deep Learning." It offers a comprehensive collection of code examples and resources designed to facilitate a deeper understanding of various deep learning concepts. The repository includes Jupyter Notebooks for each chapter, covering fundamental topics such as forward propagation, gradient descent, backpropagation, convolutional neural networks, word embeddings, recurrent neural networks (RNNs), LSTMs, and federated learning. It's an invaluable resource for individuals looking to learn deep learning through practical, hands-on examples.

handson-ml2 is a comprehensive project offering Jupyter notebooks designed to teach the fundamentals of machine learning and deep learning using Python. This second edition, though now deprecated in favor of handson-ml3, provides extensive example code and solutions to exercises, making it an excellent resource for hands-on learning and experimentation. It leverages popular libraries such as Scikit-Learn, Keras, and TensorFlow 2, covering topics from basic machine learning landscapes to advanced deep learning concepts like CNNs, RNNs, and GANs. Users can run these notebooks online via services like Colab or Kaggle, or install them locally. The project includes detailed installation instructions and addresses common issues, making it accessible for those looking to deepen their understanding of AI.

HASH is an open-source, multi-tenant platform designed for creating self-building knowledge graphs and simulations. It integrates data in near real-time and offers powerful interfaces for understanding and utilizing information across various contexts. The platform supports the deployment of intelligent, autonomous agents to grow, check, and maintain the database, integrating and structuring information from both public internet sources and private connected sources. Users, including non-technical individuals, can visually browse and manage entities (data) and types (schemas). HASH aims to serve as a source of truth for critical data, providing a foundation for high-trust, safety-assured decision-making. Future plans include evolving HASH into an all-in-one workspace with AI-generated interfaces, known as "blocks," built on strongly-typed data.

Industry-Machine-Learning is a comprehensive, curated list of applied machine learning and data science notebooks and libraries, primarily in Python using Jupyter notebooks. This GitHub repository serves as a valuable resource for professionals and researchers looking to explore real-world applications of AI across diverse sectors such as finance, healthcare, agriculture, and manufacturing. It includes projects ranging from predictive modeling and satellite data analysis to fraud detection and sentiment analysis. The project actively seeks collaboration with motivated PhD graduates and doctoral students for new research initiatives in 2024, particularly in areas like investment insights and data analysis. It also encourages community contributions to expand its catalogue of tools and notebooks.