Directory
Published directory entries matching your search.
A free LLM course from Hugging Face that teaches large language models and natural language processing. It covers the Transformers, Datasets, Tokenizers, and Accelerate libraries and the Hugging Face Hub, along with some libraries outside the ecosystem. The course is without ads.
An open source, MIT-licensed Python library imported as imblearn that relies on scikit-learn. It provides tools for classification with imbalanced classes. The documentation includes installation guides, a user guide, an API reference and a gallery of examples.
Imperial College London is a university focused on science, technology, engineering, medicine and business. It operates London campuses and an international network of hubs, and states that it uses science to tackle global challenges. Its study help pages cover undergraduate and postgraduate admissions, tuition fees, funding and scholarships, and student support. Canvas is the learning management system used at Imperial, replacing Blackboard.
Access all JetBrains IDEs, plugins, and courses for your studies and future tech career.
A beginner-friendly guide on using Keras to implement a simple neural network in Python. It walks through MNIST handwritten digit classification, covering setup, data preparation, building the model, compiling, training, testing and using the model. It is intended for complete beginners to Keras who have a basic background knowledge of neural networks.
Lambda offers hourly rental of NVIDIA H100, H200, B200, and A100 GPUs through a self-serve interface, with instances launchable via UI, API, or CLI. Users can train, fine-tune, and serve models on one to eight GPU instances and pay by the minute, with no egress fees.
A free curriculum of six courses on agentic AI design patterns for developers and product managers. It covers code, architecture, decisions and hands-on games, with 21 patterns for developers and 15 modules for product managers. No account is needed to read the material.
LearnClash is a quiz duel app in which players face a real opponent 1v1 on general knowledge or a chosen topic. Every answer is explained, and missed questions return after 7 days. Duels are turn-based with a 72-hour window per turn. Duels, explanations and missed-question reviews are free, with no ads.
Supports teaching, studying or skills practice with AI-guided learning tools.
AI-powered academic assistant for students with note-taking, essay writing, and presentation generation.
LightFM is a Python implementation of recommendation algorithms for implicit and explicit feedback. It allows item and user metadata to be incorporated into matrix factorization algorithms, representing users and items as sums of latent feature representations. Installation is available from PyPI, and a Docker setup is provided for running examples and tests.
Convert images and PDFs to LaTeX, DOCX, Overleaf, Markdown, Excel, ChemDraw and more, with our AI-powered document conversion technology.
LynxKite is a GPU-accelerated platform for graph analytics and drug discovery. It combines graph reasoning, machine learning and molecule analysis in one workflow, and offers 600+ graph operations with 2D and 3D molecule visualization. It is free and open source with a commercial tier for production teams.
Made With ML is an educational resource by Anyscale that teaches how to responsibly design, develop, deploy and iterate on production machine learning applications. Its lessons cover design, data preparation, model training, development, testing, reproducibility and production.
Supports teaching, studying or skills practice with AI-guided learning tools.
MEKA is an open source implementation of methods for multi-label learning and evaluation, based on the WEKA Machine Learning Toolkit. It includes dozens of multi-label methods from the scientific literature and a wrapper to the MULAN framework. The project is distributed via SourceForge, with code hosted on GitHub.
Memento is a free and open source, mpv-based video player intended for studying Japanese. It includes a built-in popup dictionary, uses Yomitan's dictionary format, and automates Anki card creation through AnkiConnect. It also supports grammar-aware subtitle search, mpv plugins and configuration, and streaming from websites through youtube-dl.
Microsoft Azure for Students offers access to cloud services, developer tools and $100 in Azure credits for students to build apps and explore AI and data science. Signup uses a school email, renews yearly while the user is a student, and does not require a credit card.
Middlesex University is a university in north London offering undergraduate, postgraduate and international study, research degrees and degree apprenticeships, and short courses and CPDs. The site describes career-driven teaching and student support, and lists open days, campus tours and news.
The Modernist Journals Project provides high-quality digital scans and metadata of periodicals published from 1890 to 1922, free to the public. It supports the study of modernism in the English-speaking world and includes journals such as The Crisis, Poetry, and The Little Review.
The National University of Science and Technology MISIS is a university in Moscow offering study in Russia, master's programs taught in English, admissions guidance, preparatory courses, dorms and international student support. Its scientists developed a muography-based system to inspect refinery equipment without shutting down production, using detectors that record muons.
The National Educational Panel Study (NEPS, German: Nationales Bildungspanel) is a German educational research project that provides longitudinal educational data across multiple life stages including newborns, kindergarten children, school students, and adults. It also offers data access tools, documentation, research publications, and user support resources for researchers.
A course by Andrej Karpathy on building neural networks from scratch in code, starting with backpropagation basics and building up to modern deep neural networks like GPT. Prerequisites are solid Python programming and intro-level math such as derivatives and gaussians.
NN Visual is an interactive web-based neural network visualizer. It lets users configure hidden layers, select datasets such as auto_mpg, iris, xor, or mnist, and train a network while observing forward and backpropagation step by step. The tool displays training loss, mean absolute error, weight distributions, and node activation brightness. Written explanations accompany the visualizations to teach concepts like gradient descent, weights, biases, and activation functions without requiring code.
