Open Source Java Machine Learning Software - Page 5

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

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.

*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.

“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.

P53 Cancer Rescue Project, University of California, Irvine , Samuel A. Danziger, Christopher Wassman, Faezeh Salehi Amiri, Roberta Baronio, Linda Hall, Rainer K. Brachmann, G. Wesley Hatfield, Peter Kaiser, Richard H. Lathrop

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).

The Information Extraction Plugin allows the use of information extraction techniques within RapidMiner. It can be seen as an interface between natural language and IE- or datamining-methods, by extracting interesting information out of documents.

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.

Scene is a computer vision framework that performs background subtraction and object tracking, using two traditional algorithms and three more recent algorithms based on neural networks and fuzzy classification rules. For each detected object, Scene sends TUIO messages to one or several client applications. The present release features GPU accelerated versions of all the background subtraction methods and morphological post processing of the object blobs with dilation and erosion filters, implemented in OpenCL. The framework was mainly designed as a toolkit for the rapid development of interactive art projects that explore dynamics of complex environments. The Scene GUI runs and compiles under Windows, Linux, and MacOS X, and is available in both 32 bit and 64 bit versions.

A java tool for anytime and interactive sequence mining. Aims at providing users with a way of analyzing her activity traces and extract activity schemes from them.

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.

Smile is a fast and comprehensive machine learning engine. With advanced data structures and algorithms, Smile delivers the state-of-art performance. Compared to this third-party benchmark, Smile outperforms R, Python, Spark, H2O, xgboost significantly. Smile is a couple of times faster than the closest competitor. The memory usage is also very efficient. If we can train advanced machine learning models on a PC, why buy a cluster? Write applications quickly in Java, Scala, or any JVM languages. Data scientists and developers can speak the same language now! Smile provides hundreds advanced algorithms with clean interface. Scala API also offers high-level operators that make it easy to build machine learning apps. And you can use it interactively from the shell, embedded in Scala. The most complete machine learning engine. Smile covers every aspect of machine learning.