Directory
Published directory entries matching your search.
An arXiv paper on discovering skylines over hidden web databases whose search interfaces enforce a top-k output constraint. It examines how search interface controls affect discovery cost and develops algorithms for one-ended range, free range and point predicates, combined for mixed interfaces. Experiments over real-world online and offline databases are reported.
An arXiv paper on digging deeper into hidden web databases limited by the top-k output constraint. It presents the GetNext meta-algorithm, which retrieves the next ranked tuple through a restrictive interface without prior knowledge of the ranking function, and algorithms that generate and execute multiple reformulated queries. Theoretical analysis and experiments over synthetic and real-world databases are reported.
Python examples of popular machine learning algorithms with interactive Jupyter demos and math being explained.
An art project by Tijmen Schep that demonstrates how face detection algorithms judge faces. It runs in the browser and requires camera access, while processing data locally without sending personal data to a server. It was made as part of the European Union's Sherpa research program.
Hyperas is a wrapper that combines Keras model definition with Hyperopt hyperparameter optimization. Users define models as usual and wrap parameters in double curly brackets with a chosen distribution. It is installed via pip and runs optimization using algorithms such as TPE with a set number of evaluation runs.
Hypernets is a general AutoML framework for building automatic optimization tools for machine learning frameworks and libraries, including tensorflow, keras, pytorch, sklearn, lightgbm and xgboost. It offers an abstract search space representation covering hyperparameter optimization and neural architecture search, with optimization algorithms such as evolution algorithm and Monte Carlo tree search.
ImageFoo is an image optimizer that compresses images using advanced algorithms that detect and analyse images, then compresses them to a quality chosen by the user. Users drag or click to add images and hit optimize. It supports both Windows and Android devices and compresses multiple types of images.
A University of Maryland lecturer's page linking to notes and resources for mathematics and computer science courses, including calculus, differential equations, linear algebra, abstract algebra, number theory, and algorithms. It also offers standalone class notes applicable to multiple courses.
InstallForge is a free tool for creating setup packages for Windows. It uses a wizard-driven interface that requires no scripting knowledge, and its packages are distributed as single executable files built on a native setup engine. It supports multiple Windows versions, multilingual packages, customizable setup dialogs and several compression algorithms.
J Perm is a speedcubing tutorial site offering guides for solving 3x3, 2x2 and 4x4 cubes, including the CFOP method, blindfolded solving and one-handed techniques. It also provides algorithm trainers and sections on cube reviews, example solves and F2L algorithms.
JpegMedic ARWE is a tool for automatic batch recovery of JPG files partially encrypted by ransomware. It offers two recovery modes, one requiring a non-damaged JPG file from the same camera and settings, and one using heuristic algorithms. It can also extract JPG thumbnails from encrypted RAW files. It is described as a smaller sibling of JpegMedic.
KerasTuner is a hyperparameter optimization framework for Keras. It provides a define-by-run syntax for configuring search spaces and includes Bayesian Optimization, Hyperband and Random Search algorithms. It requires Python 3.8+ and TensorFlow 2.0+.
lambda-ml is a small machine learning library written in Lisp, specifically Clojure, aimed at simple, concise implementations of machine learning techniques and utilities. It covers supervised algorithms such as neural networks, decision trees, ensemble methods, k-nearest neighbors, linear and logistic regression, naive Bayes and random forest, plus unsupervised methods including DBSCAN, hierarchical clustering, k-means and non-negative matrix factorization.
Learn X in Y minutes is a community-driven site offering brief tours of programming languages, plus frameworks and libraries, tools, and algorithms and data structures. Language pages are available in numerous translations, including English, French, German, Spanish and Chinese.
An introductory machine learning course taught by Caltech Professor Yaser Abu-Mostafa, recorded from a live broadcast and available as a free online MOOC. It covers basic theory, algorithms and applications across 18 lectures, with homework sets and a final exam. Prerequisites are basic probability, matrices and calculus.
The Libra Toolkit is a collection of algorithms for learning and inference with discrete probabilistic models, including Bayesian networks, Markov networks, dependency networks, sum-product networks and arithmetic circuits. Each algorithm is implemented as a command-line program with consistent options and file formats, and all methods are written in OCaml.
LilyPond is a free music engraving program in the GNU Project that produces sheet music through text input. Its style settings, font designs and algorithms are inspired by hand-engraved music. It handles classical music, complex notation, tablature, vocal music, lead sheets and orchestral projects.
Machine Learning in MatLab/Octave is a collection of MatLab/Octave implementations of popular machine learning algorithms, including code examples and explanations of the associated mathematics. It covers supervised learning tasks such as regression and classification as well as unsupervised learning.
Machine Learning Mastery is a website that provides educational content such as tutorials, quick start guides, and eBooks to help developers learn and apply machine learning concepts and algorithms. It covers topics like deep learning, computer vision, natural language processing, and specific libraries including TensorFlow, PyTorch, and scikit-learn.
Magenta is a research project exploring machine learning in art and music creation, developing deep learning and reinforcement learning algorithms for generating songs, images, and drawings. It also explores tools letting artists and musicians extend their processes with these models. The repository is archived and read-only.
A repository of material for the exercise classes of a Big Data Analytics master course. Hands-on sessions cover Spark and its machine learning library, Map/Reduce implementations of linear regression and alternating least squares, streaming analytics with Recursive Least Squares, and image classification with convolutional neural networks. Material is provided as Jupyter notebooks.
MatlabBGL is a Matlab package for working with graphs that uses the Boost Graph Library to implement graph algorithms. It is designed for large sparse graphs with hundreds of thousands of nodes and was written by David Gleich. The page lists version 4.0 as the latest release, with downloads hosted on the Matlab File Exchange.
MDCalc is a source for medical equations, algorithms, scores, and guidelines. It offers a library of calculators, including the Cockcroft-Gault creatinine clearance equation, a weight-based levothyroxine dose calculator, CKD-EPI GFR equations, mean arterial pressure, and the SpO₂/FiO₂ ratio. Tools can be browsed by specialty and filtered by calculation purpose.
Metric Learning Algorithms in Python.
