Research & Education

3D-Machine-Learning is a comprehensive GitHub repository dedicated to curating resources in the interdisciplinary field of 3D machine learning. It functions as a dynamic study note and a platform for triaging new research papers, covering topics from 3D pose estimation to scene synthesis. The repository categorizes resources using distinct icons for different 3D representations like multi-view images, volumetric data, point clouds, polygonal meshes, and primitive-based models. It also provides links to related academic papers through Connected Papers for visualizing research relationships. The project encourages community involvement through pull requests and a Slack workspace to foster collaboration and knowledge sharing among researchers and enthusiasts.

AttentionDeepMIL offers a PyTorch implementation of Attention-based Deep Multiple Instance Learning, a technique detailed in the paper "Attention-based Deep Multiple Instance Learning" by Ilse, Tomczak, and Welling. This open-source tool is designed for researchers and developers to explore and apply attention mechanisms within deep learning models, particularly in the context of multiple instance learning. It includes code for running MNIST-BAGS experiments and provides guidance for adapting the model to histopathology datasets like Breast Cancer and Colon Cancer. The implementation features a modified LeNet-5 model with Attention-based MIL pooling and uses the negative log-likelihood of the Bernoulli distribution as its objective function. It's a valuable resource for those looking to replicate or extend research in this specialized area of deep learning.

Eofis is a comprehensive learning platform designed to streamline the educational process through auto-generation, collaboration, and auto-scheduling. It offers a unified learning experience across various operating systems including Windows, Apple, Linux, iOS, and Android. The Eofis Chrome Extension is a key feature, enabling users to effortlessly add material from any webpage directly to their Eofis library. Utilizing AI algorithms, the extension transforms this content into questions, facilitating an interactive and efficient study method. Core features include auto-generation of questions from web pages and PDFs, visual concept maps for organizing notes, adaptive scheduling, Google Calendar integration, and multi-format question practice like flashcards and minigames, alongside collaboration tools for group study.

Senken is a platform designed to simplify and secure the procurement of high-quality carbon credits for businesses. It employs a rigorous, science-backed standard to evaluate carbon projects, analyzing over 600 data points through its Sustainability Integrity Index (SII). This process ensures that only the top 5% of verified carbon credits are offered, mitigating greenwashing risks and ensuring compliance with standards like Oxford Principles, ICVCM, and CSRD. Senken provides end-to-end support, from strategic advisory and procurement to audit defense with its 'Champion's Kit,' which includes executive summaries, due diligence data, and impact slides for stakeholders. The platform aims to provide transparency and defensibility in carbon compensation, addressing the market reality where many carbon credits fail independent analysis.

approachingalmost is a GitHub repository that serves as a companion to the book "Approaching (Almost) Any Machine Learning Problem." This resource offers valuable insights and practical code examples for individuals looking to tackle various machine learning challenges. While the repository does not share the complete code from the book, it provides environment files and references to datasets, encouraging users to code along and understand the concepts. It is designed to support machine learning practitioners and data scientists in their learning journey, offering a structured approach to solving complex problems. Users can find links to purchase the book from various regional Amazon stores and Pothi, as well as instructions for setting up the development environment.

Speak is an AI-powered mobile application designed to help users achieve fluency in new languages through immersive conversational practice. It provides real-time feedback on pronunciation, intonation, and grammar, fostering confidence in speaking from day one. Users engage in interactive lessons, role-play scenarios, and open-ended conversations with an advanced AI tutor, making language learning accessible and effective for all levels. The platform focuses on getting users to speak out loud as much as possible, offering a personalized curriculum and the ability to practice on any topic, anytime, anywhere. Speak aims to be the most effective way to learn a language by providing a dedicated AI tutor available 24/7.

Amsterdam Data Science, despite its name, functions as a review platform for online casinos, specifically those not affiliated with the Dutch Cruks exclusion system. The site offers detailed reviews and rankings of various 'No Cruks' casinos, evaluating them based on six key criteria: licensing and reliability, payout speed and limits, bonus conditions, game offerings, payment methods, and customer service. It highlights welcome bonuses, free spins, and other promotional offers, along with minimum deposit requirements and unique features of each casino. The platform aims to guide Dutch players in choosing reliable international online casinos.

async-rl offers a practical implementation of asynchronous 1-step Q learning, as detailed in the paper "Asynchronous Methods for Deep Reinforcement Learning." This open-source project leverages Tensorflow and Keras for deep Q network definition and optimization, while integrating with OpenAI's Gym library for interaction with the Atari Learning Environment. A key feature is its use of multiple actor-learner threads, which helps stabilize the learning process without relying on memory-intensive experience replay, making it efficient for machines with less RAM. The repository also includes a work-in-progress asynchronous advantage actor-critic implementation and provides instructions for training, visualizing with TensorBoard, and evaluating models.

The AI Accelerator Institute serves as an independent, knowledge-sharing platform dedicated to connecting and inspiring AI experts and machine scientists globally. It offers a community membership that provides access to a library of members-only articles, discounts on AI events, and over 250 hours of event footage. Members can join a Slack community to network with peers, exchange ideas, and discover job opportunities. The institute also hosts various events, from webinars to in-person summits, leadership dinners, and members-only meetups, designed to educate and connect professionals in the AI field. Additionally, it publishes reports, guides, and podcasts, focusing on accelerating AI at the edge and fostering the next generation of machine intelligence.

Quizmaster101 provides a weekly online quiz focused on current world news and events. Users can sign up to participate in timed quizzes, track their performance on leaderboards, and compete for cash prizes. The platform releases 10 new questions every Sunday at 12pm GMT, challenging participants' knowledge of the past seven days' news. While a free option exists for the first 100 users, a monthly subscription is required to continue playing after that. The site emphasizes fair play with strict rules against bots and collaboration, fostering a competitive environment for news enthusiasts.

+ATLANTIC is a Portuguese Collaborative Laboratory (CoLAB) dedicated to leveraging marine science and ocean technology for sustainable development. The platform focuses on addressing real-world challenges related to oceans, coastal zones, climate, and the environment. It specializes in transforming complex scientific data into practical, actionable products and services. Utilizing advanced AI, data science, and geospatial analysis, +ATLANTIC supports various stakeholders including governance bodies, economic sectors, research institutions, and innovation initiatives across the Atlantic region, promoting a sustainable blue economy. Its work contributes to informed decision-making and innovative solutions for marine and coastal ecosystems.

Math Ai - Homework Helper is a mobile application designed to assist students with their mathematics homework. Users can easily input problems by taking a photo of the question or typing it directly into the app. The tool then provides instant, detailed, step-by-step explanations, making it easier for students to understand the solution process. It covers a wide range of mathematical subjects, including algebra, geometry, and calculus. This AI-powered helper acts as a personal tutor, offering 24/7 assistance to help users grasp concepts, improve their problem-solving skills, and ultimately enhance their overall math proficiency.

Jiroshi is a software-as-a-service platform designed for educators and organizations to build, manage, and operate their own online learning platforms. It functions as a headless Learning Management System (LMS), providing clean, flexible APIs for content, user, and enrollment management, eliminating the need to build an LMS from scratch. Key features include secure JWT-based student authentication, an instructor dashboard for managing courses and students, and developer-first REST APIs with detailed documentation. Jiroshi supports flexible course modeling and allows users to bring their own frontend frameworks, enabling rapid launch of custom learning portals. The platform also handles heavy lifting like video hosting and user management, with future plans for built-in payment processing.

koko AI is an innovative language learning application designed to help users speak Korean with confidence. It offers real conversation practice with an AI tutor, allowing learners to master both 존댓말 (formal speech) and 반말 (casual speech). The app provides instant feedback on pronunciation and grammar, making it an effective tool for improving fluency. Users can practice anytime, anywhere, making it convenient for busy schedules. The platform is backed by prominent names like OpenAI, Google, Supabase, ElevenLabs, and PostHog, ensuring a robust and technologically advanced learning experience. It's ideal for absolute beginners looking to build a strong foundation in Korean speaking.

Dori Speak AI English Learning is a mobile application designed to make learning English speaking fun and engaging through AI-powered conversations. Users can choose from hundreds of AI tutors and character scenarios to practice speaking in various situations, from daily life to professional settings. The platform addresses common challenges like fear of speaking, lack of real-life practice opportunities, and absence of immediate error correction. Dori provides instant feedback, AI key summaries, and analysis of conversations to highlight strengths and weaknesses, helping users build confidence and improve fluency without pressure. It supports learning multiple languages beyond English, including Spanish, Japanese, and Korean.

CEIMIA (Centre d'expertise International de Montréal en intelligence artificielle) is an international center dedicated to the responsible development of AI. It operates on principles of ethics, human rights, inclusion, diversity, innovation, and economic growth. CEIMIA develops and implements high-impact applied projects in responsible AI, focusing on areas such as AI for the environment, AI for health, data governance for AI, and human rights in AI. The organization aims to provide tools and approaches for integrating effective governance and human rights throughout the AI lifecycle, collaborating with various stakeholders to achieve its mission.

awesome-deep-vision is a curated list of deep learning resources specifically tailored for computer vision. Inspired by other 'awesome' lists, it serves as a valuable repository for researchers and practitioners in the field. The repository categorizes resources into various topics such as ImageNet Classification, Object Detection, Object Tracking, Low-Level Vision, Semantic Segmentation, and more. It includes links to academic papers, code implementations, courses, books, videos, and software frameworks, making it a central hub for discovering relevant materials. While the project is not actively maintained, it remains a useful historical reference for foundational and influential works in deep learning for computer vision.

Awesome-Deepfake-Generation-and-Detection is an open-source GitHub repository offering a detailed survey on deepfake generation and detection, specifically focusing on facial manipulation. It encompasses areas such as Face Swapping, Face Reenactment, Talking Face Generation, Face Attribute Editing, and Forgery Detection. The resource also delves into related domains like Head Swap, Face Super-resolution, Face Reconstruction, and Portrait Style Transfer. It aims to be the most comprehensive survey on these topics, providing detailed results for representative works and encouraging contributions from the research community to keep the repository updated with missing papers and new suggestions.

awesome-computer-vision-models is a comprehensive, curated list of popular deep learning models specifically designed for computer vision tasks. This open-source repository serves as a valuable resource for researchers and engineers, offering detailed information on classification, segmentation, and detection models. Each entry includes crucial evaluation metrics such as the number of parameters, FLOPS, and various error rates (e.g., Top-1 Error, Top-5 Error, mIOU), along with the publication year. The repository helps users quickly identify and compare models based on their performance and resource requirements, facilitating informed decisions for their projects. It's an essential reference for anyone working with deep learning in computer vision.

awesome-equivariant-network is a comprehensive, curated list of research papers focused on equivariant neural networks. This GitHub repository is designed as a dynamic resource for academics, researchers, and practitioners interested in the theoretical foundations, applications, and advancements in equivariant neural networks. It categorizes papers into key areas such as Equivariance and Group convolution, Equivariant Density Estimation and Sampling, and various applications. The list is actively maintained and welcomes contributions, ensuring users can stay updated on the latest developments and seminal works in this specialized domain of AI.

awesome-diarization is a comprehensive, curated list of resources dedicated to speaker diarization. This open-source repository organizes a wide array of materials, including academic papers covering various topics like LLM-enhanced diarization, supervised and online diarization, and joint diarization with ASR. It also features a collection of software frameworks and libraries, such as FunASR, SpeechBrain, and pyannote-audio, available in multiple programming languages like Python, Java, and C++. Additionally, it provides information on evaluation tools, clustering algorithms, speaker embedding methods, and relevant datasets, making it an invaluable resource for researchers and developers in speech technology.

Awesome-3D-Object-Detection is a comprehensive curated list of resources dedicated to deep learning for 3D Object Detection, with a strong emphasis on lidar-based methodologies. This GitHub repository serves as an invaluable hub for researchers and engineers, providing direct links to relevant academic papers, associated code implementations, and essential datasets like KITTI, nuScenes, Lyft, and Waymo Open Dataset. It also highlights top conferences and workshops in the field, offering a structured overview of the latest developments and trends. The resource includes surveys, books, videos, and course materials, making it a one-stop reference for anyone looking to delve into or stay current with 3D object detection.

SmartVocab is an AI-powered English vocabulary coach designed to make learning engaging, entertaining, and enlightening. The platform focuses on contextual and visual learning, utilizing movies, short stories, novels, speeches, and quotes to introduce new vocabulary. Users can improve their English proficiency through visual flashcards, understanding root words, and curated word lists. The tool aims to provide a personalized and scientific approach to vocabulary acquisition, making it suitable for individuals looking to enhance their English communication skills or prepare for standardized tests. It offers a comprehensive learning experience that combines watching, playing, and learning.

awesome-deep-learning is an extensive, curated list designed for anyone interested in Deep Learning. It serves as a central hub for discovering high-quality educational materials and community resources. The list encompasses a wide array of content, from foundational books and university courses to insightful videos, academic papers, and practical tutorials. It also highlights researchers, relevant websites, datasets, conferences, and various frameworks and tools, making it an invaluable resource for both beginners and experienced practitioners looking to deepen their understanding or find specific information within the Deep Learning domain.