Weka4OC: Weka for Overlapping Clustering is a GUI extending WEKA
This is a GUI application for learning non disjoint groups based on Weka machine learning framework. It offers a variety of learning methods, based on k-means, able to produce overlapping clusters. The application also contains an evaluation framework that calculates several external validation measures. The application offers a visualization tool to discover overlapping groups.
speech recognition software for Polish language
Software for speech recognition in Polish language. Large vocabulary continuous speech recognition (LVCSR) and Commands. SkryBot recognises speech in Polish language and changes it into text by using: 1.microphone, 2.sound files (turned off in demo version). SkryBot recognises dictated speech and converts it into text. This means, that if you speak to the microphone or you use earlier recorded sound file, SkryBot will change it into text. SkryBot offers you: 1. audio conversion and cutting sound files into smaller ones, 2. searching for words or phrases in sound files (recognised by SkryBot), 3. editing sound files and automatic cutting off long silence parts in the recording, 4. improving accuracy of recognition. Versions of SkryBot: 1. SkryBot Prawo - for courts, lawyers, police, 2. SkryBot Administracyjny - for civil and government administration, 3. SkryBot Medycyna Rodzinna - for doctors, hospitals. https://sourceforge.net/p/skrybotdomowy/wiki/Home
Scientific computing, machine learning and computer vision for .NET
The Accord.NET Framework provides machine learning, mathematics, statistics, computer vision, computer audition, and several scientific computing related methods and techniques to .NET. The project is compatible with the .NET Framework. NET Standard, .NET Core, and Mono.
Texas Holdem Poker AI
Full ring Texas Hold'em poker game built around an intelligent AI system. The AI uses players' betting actions to calculate a probability distribution of their hole cards and uses it to evaluate hand strength and the best possible action. Small random changes are made to mimic human behavior and make the AI less predictable. Future versions will include adaptive opponent modeling using neural networks to improve the AI's strength. The AI code can be easily adapted for input from screen scrapers.
This project includes basic NLP and DSP techniques for Text-to-Speech
See TTS demo at: http://rslp.racai.ro/index.php?page=tts This is an entirely written in JAVA project which includes a set of tools and methods designed to enable Multilingual Text-to-Speech (TTS) synthesis. We currently support English and Romanian but we will soon train more models and make them available for download. If you want to read more about our other NLP and TTS tools check out http://nlptools.racai.ro.
Non-disjoint groupping of Documents based on word sequence approach
This is a GUI for learning non disjoint groups of documents based on Weka machine learning framework. It offers the possibility to make non disjoint clustering of documents using both vectorial and sequential representation (word sequence approach based on WSK kernel). All data format supported by WEKA could be used in DocCO. Data could be loaded from files, from databases or from specified URL. All the preprocessing techniques implemented in WEKA could be used before performing the learning.
Weka wrapper for the SGM toolkit for text classification and modeling.
Weka wrapper for the SGM toolkit for text classification and modeling. Provides Sparse Generative Models for scalable and accurate text classification and modeling for use in high-speed and large-scale text mining. Has lower time complexity of classification than comparable software due to inference based on sparse model representation and use of an inverted index. The provided .zip file is in the Weka package format, giving access to text classification. Other functions are usable through either Java command-line commands or class inclusion into Java projects.
a dbms for neural nets. Chatbots, DTrees, random forests, n-grams,...
This project consists out of a windows based designer application and a library (that can run on multiple platforms, including android) together with several demo applications (including an MVC3 chatbot client and an android application). It is probably best compared to a database management system, but for neural networks instead of relational data. As such, the library is optimized for handling any type of data-size by using advanced streaming and caching algorithms. With the designer, you are able to create different types of decision trees, random forests, n-grams, pattern-matchers, conversational agents and all sorts of AI related algorithms. You can combine statistical approaches as well as pattern matchers or others. Do natural language processing, image or data analysis & interpretation,...
Scientific Visualisation Made Easy
The Simple Medical Imaging Library Interface (SMILI), pronounced 'smilie', is an open-source, light-weight and easy-to-use medical imaging viewer and library for all major operating systems. The main sMILX application features for viewing n-D images, vector images, DICOMs, anonymizing, shape analysis and models/surfaces with easy drag and drop functions. It also features a number of standard processing algorithms for smoothing, thresholding, masking etc. images and models, both with graphical user interfaces and/or via the command-line. See our YouTube channel for tutorial videos via the homepage. The applications are all built out of a uniform user-interface framework that provides a very high level (Qt) interface to powerful image processing and scientific visualisation algorithms from the Insight Toolkit (ITK) and Visualisation Toolkit (VTK). The framework allows one to build stand-alone medical imaging applications quickly and easily.
Simulation of many neural networks on a 2D map with evolution.
Simulation of many neural networks on a 2D map with evolution.
This is an Internet resource management system that can be used to control both internet and network access of a registered or unregistered user on all kinds of network.
This work consists in building a Java Text mining toolkit based on what exists nowadays in the field of knowledge discovery from data collections.
This is C++ application code that implements Gene Expression Programming, or GEP - a form of genetic algorithm.
Spec is a voice control based on the libraries of Sphinx-4.
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
The STAIR Vision Library (SVL), originally developed to support the STanford AI Robot, provides software infrastructure for computer vision, machine learning, and probabilistic graphical models.
SMILE = Speech & Music Interpretation by Large Space Extraction openSMILE is a fast, real-time (audio) feature extraction utility for automatic speech, music and paralinguistic recognition research developed originally at TUM in the scope of the EU-project SEMAINE, now maintained and supported by audEERING.
A genetic programming library made in C#. A very easy library to use, The user can use this library in order to randomly generate and evolve programs. Current version 0.2
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).
Open Source - Ruby Program Make your computer live, your computer now will be able to recognize and respond in many different languages. Customizable settings, create a personality for the computer. Give life to your computer!
R-Portfolio - breakeven optimally diversified investment portfolio. Оптимально диверсифицированный инвестиционный портфель.
Utility converts the weights file of a MLP Breadboard into a formula
The NeuroSolutions: Formula Generator utility converts the weights file of a default MLP breadboard (1-hidden layer with a TanhAxon in the hidden layer and either a TanhAxon or BiasAxon in the output layer) into a usable formula that can be copied and pasted into your own programs to compute the output of the trained neural network.
Machine Learning Python
mlpy is a Python module for Machine Learning built on top of NumPy/SciPy and of GSL. mlpy provides high-level functions and classes allowing, with few lines of code, the design of rich workflows for classification, regression, clustering and feature selection. mlpy is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 3. mlpy is available both for Python >=2.6 and Python 3.X.