Open Source Java Machine Learning Software - Page 5

ML@IUL is a class-project of the Machine Learning (ML) course at DCTI (Department of Computer Science and Technology), IUL (ISCTE - Lisbon University Institute). The objective is to create an ML library from student assignments.

A Machine Learning and Data Retrieval Framework

Maui is a multi-purpose automatic topic indexing algorithm. Given a document, Maui automatically identifies its topics. Depending on the task topics are tags, keywords, keyphrases, vocabulary terms, descriptors or Wikipedia titles.

An open-source system for Machine Learning model versioning, metadata, and experiment management. ModelDB is an open-source system to version machine learning models including their ingredients code, data, config, and environment and to track ML metadata across the model lifecycle.

This Java-application contains all required components to simulate a game of Ms. Pac-Man and let an agent learn intelligent playing behaviour using reinforcement learning and either Q-Learning or SARSA. The framework was developed by Luuk Bom and Ruud Henken, under supervision of Marco Wiering, Department of Artificial Intelligence, University of Groningen. It formed the basis of a bachelor's thesis titled "Using reinforcement learning with relative input to train Ms. Pac-Man", L.A.M. Bom (2012).

This is a RapidMiner extension replacing the current Weka-Plugin with the updated 3.7.3 Weka-Version. This is basically a branch of the 3.7.3 Version of WEKA wrapped into the old extension. New Features Include: -All the Features of the 3.7.3 Weka Package -Multi-Threaded ensemble learning -An enhancement on the popular RandomForest Learner based on "Dynamic Integration with Random Forests" by Tsymbal et al. 2006 and "Improving Random Forests" by Robnik-Sikonja 2004. -More enhancements to the voting mechanisms in Random Forest -Possibility to output Feature Weights according to the original Breiman Paper 2001

*NOTICE* The official software(NGSpop) will be updated soon, so please visit us in 2/29. Thank you.

It can predict digits from 0-9 with Artificial Neural Network. I trained ANN with 100 samples of each digit. It takes input of 20x20 pixel image and predicts it with Neural Network. It may predict wrong digit due to very low sample data but it work 90% correctly. Note: JRE 1.6 is required to run this application.

3-layer neural network for regression and classification with sigmoid activation function and command line interface similar to LibSVM. Quick Start: "java -jar nen.jar"

“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

An implementation of Back Propagation Neuron Network

Feature construction and selection are two key factors in the field of Machine Learning (ML). Usually, these are very time-consuming and complex tasks because the features have to be manually crafted. The features are aggregated, combined or split to create features from raw data. This project makes use of ontologies to automatically generate features for the ML algorithms. The features are generated by combining the concepts and relationships that are already in the knowledge base, expressed in form of ontology.

OpenIMAJ: The Open toolkit for Intelligent Multimedia Analysis in Java. OpenIMAJ contains a large collection of pure-Java classes for analysing multimedia documents, from tools for extracting image features, to tools for analysing web pages.

Optex Analyzer is a software to analyze and compare algorithms to solve approximately optimization problems. It has a GUI that allows select a set of input files containing raw algorithm results. The analysis is shown with tables and charts.

This project aims to develop a method to identify communities in a social network according to some point of view.

R-Portfolio - breakeven optimally diversified investment portfolio. Оптимально диверсифицированный инвестиционный портфель.

An experimental unsupervised learning method for improvising jazz melodies, based on restricted Boltzmann machines (RBMs) layered into Deep Belief Networks (forms of neural networks).

This software uses a genetic algorithm to "evolve" reactor designs for Schema's space-simulation game, Star-Made (http://star-made.org/). One of the more unique aspects of the game is that ship power management is not as simple as filling a cube with power generation blocks. This mechanism leads to difficulties in getting maximal power generation out of such reactors. This program rectifies this issue by using a self-organizing variant of brute force search. Much of the search space is pruned early on by a user-selectable fitness function. Within a few epochs, reactor output quickly converges to several sub-optimal, yet high-output reactors. Given enough time, the idea is that the optimal reactor configuration will be yielded.

Reconcile is an open source research platform for coreference resolution. It combines a large number of open source NLP components and provides extension points for researchers to plug in additional features and techniques.

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.

This application allow user to predict dissolution profile of solid dispersion systems based on algorithms like symbolic regression, deep neural networks, random forests or generalized boosted models. Those techniques can be combined to create expert system. Application was created as a part of project K/DSC/004290 subsidy for young researchers from Polish Ministry of Higher Education.

Sanchay is a collection of tools and APIs for language researchers. It has some implementations of NLP algorithms, some flexible APIs, several user friendly annotation interfaces and Sanchay Query Language for language resources.

Seldon Server is a machine learning platform and recommendation engine built on Kubernetes. Seldon reduces time-to-value so models can get to work faster. Scale with confidence and minimize risk through interpretable results and transparent model performance. Seldon Core focuses purely on deploying a wide range of ML models on Kubernetes, allowing complex runtime serving graphs to be managed in production. Seldon Core is a progression of the goals of the Seldon-Server project but also a more restricted focus to solving the final step in a machine learning project which is serving models in production. Seldon Server is a machine learning platform that helps your data science team deploy models into production. It provides an open-source data science stack that runs within a Kubernetes Cluster. You can use Seldon to deploy machine learning and deep learning models into production on-premise or in the cloud (e.g. GCP, AWS, Azure).

SAIM allows to interlink knowledge bases in the Semantic Web. It focuses on instance matching of very large knowledge bases available as SPARQL endpoints. SAIM uses machine learning techniques and is compatible with SILK.