General-purpose, compute-optimized, or GPU/TPU-accelerated. Built to your exact specs.
Live migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
Start Free
Build Agents and Models on One Platform
Everything you need to build production-ready agents and models. Access 200+ Google and third-party AI models and tools.
Gemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
This project is devoted to the creation of an open source Error-Correcting Output Codes (ECOC) library for the Machine Learning community. The ECOC framework is a powerful tool to deal with multi-class categorization problems.
“Neurology Diagnosis System” is a web-based expert system for diagnosis of neurologic disorders or the disorders of our nervous system. Health assistants in remote areas can use the system to diagnose neurologic patients in the absence of neurolo
DOGMA is a MATLAB toolbox for discriminative online learning. It implements all the state of the art algorithms in a unique and simple framework. Examples are Perceptron, Passive-Aggresive, ALMA, NORMA, SILK, Projectron, RBP, Banditron, etc.
This RapidMiner-plugin consists of operators for feature selection and classification - mainly on high-dimensional (microarray-) data - and some helper-classes/operators.
MoMS (Model Management System) is a model management system for statistical models, a little bit like a database management system. Instead of having tables, we have models that can be updated and queried.
This Project is to make a robotic platform and Soft Brain for a self learning research robot.
For making it modular we are using OSGI with rosjava javacv.
A simple experiment into machine learning using the psychological principles of operant conditioning, spontaneous recovery and extinction. The main idea is that the "pet" in question knows nothing and you must teach it what certain keystrokes mean.
An agent-based situated language learning simulation that focuses on lexical learning and grounding, featuring a unigram syntax structure and a CFG-based semantic grammar. Created as a MSc thesis project, using python.
Lay a foundation for success with Tested Reference Architectures developed by Fortinet’s experts. Learn more in this white paper.
Moving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
Content-based Image Retrieval (CBIR) consists of retrieving visually similar images to a given query image from a database of images. It is done by comparing selected visual features such as color, texture and shape from the image database.
Enable the user to talk to the calculator to enter the numbers and operations or write them using a drawing panel , it support both English and Arabic languages.It have text to speech of the entered numbers/operations and reading the results.
This project intends to create a bacteria simulator framework, with some realistic bacteria control methods based on chemical signaling, simple sensors, motors and neural networks. The bacteria will evolve in a genetic algorithm environment.
The Mars Rover Simulator project is based on the evolutionary robotics paradigm where an artificial agent acquires its skills through the process of artificial evolution. This simulator can be useful to evolve neural network controllers for the rover
BIL++ is a set of standalone C++ packages for data processing in Bioinformatics (Graph mining, Bayesian networks, Genetic algorithm, Discretization, Gene expression data analysis, Hypothesis testing).
RobGP is a genetic programming system written from the ground up in C++. It's primary goals are efficiency, ease of use, and extensibility. It's distinguishing feature is that it has a modified version of Koza's architecture altering operations.
A system that shall predict good days and locations for cross country free flying such as paragliding by comparing current weather predictions with statistics about past weather predictions and flights from online contests.
MultiViL is a tool for multi-view learning. It supports four classifiers (KNN, Naive-Bayes, Rochio and SVM-Perf), four view combining methods (Majority Voting, Borda Count, Dempster-Shafer theory of evidence and PSO) and provides many analisys tools.
The Python Computer Vision Framework is an opened project deisgned for all those interested in computer vision. It aims at making computer vision more easy and structured and matlab-free.
It may also be used for other artistic and scientific areas.
RoboBeans is an interface to the "Robocup 2D Soccer Simulation Server" that allows developers to write Robocup teams\agents concentrating on behaviour and AI without having to worry about syntax of communication or network issues.