background preloader

AI

Facebook Twitter

Framework. AForge.NET is an open source C# framework designed for developers and researchers in the fields of Computer Vision and Artificial Intelligence - image processing, neural networks, genetic algorithms, fuzzy logic, machine learning, robotics, etc.

Framework

Google DeepMind. ArXiv 2014 Neural Turing Machines Neural Turing Machines (NTMs) couple differentiable, external memory resources to neural network controllers.

Google DeepMind

Download Free Windows Artificial Intelligence Open Source Software - SourceForge. GRATF. GRATF stands for Glyph Recognition And Tracking Framework.

GRATF

The project is aimed to provide a library which does localization, recognition and pose estimation of optical glyphs in still images and video files. The library can be used in robotics applications for example, where glyphs may serve as commands or directions to robots. However, most popular application of optical glyph recognition is augmented reality. Here are few demos which were made using the GRATF project. For detailed description of algorithms implemented in this project, you are welcome to read next series of articles: The project includes: Glyph recognition and pose estimation library, which is an extension to AForge.NET framework.

In the case you have found any bugs/issues, please, feel free to register them in the issues tracking system. Framework. AForge.NET is an open source C# framework designed for developers and researchers in the fields of Computer Vision and Artificial Intelligence - image processing, neural networks, genetic algorithms, fuzzy logic, machine learning, robotics, etc.

Framework

The framework is comprised by the set of libraries and sample applications, which demonstrate their features: Fast Artificial Neural Network Library (FANN) Dlib C++ Library. Armadillo: C++ linear algebra library. CLIPS: A Tool for Building Expert Systems. Iplab - Image Processing Lab. Image Processing Lab is an image processing application written in C#, which includes different filters and tools to analyze images available in AForge.NET Framework.

iplab - Image Processing Lab

The following filters are available in the IPLab application: It is possible to create (save and load) your own convolution filters or filters based on standard mathematical morphology operators. Colorized grid makes it very convenient to work with custom convolution filters. A preview window allows to view results of changing filters' parameters on the fly. It is possible to scroll an image using mouse in preview area.

A Photo Shop like histogram allows to get information about mean, standard deviation, median, minimum and maximum values. The application allows to copy to or paste from clipboard, save and print images.

Fuzzy

Machine Learning. MIT AI Aries Group Home Page. Neural Net. Ortech Engineering's Fuzzy Logic Reservoir. Rorchard/FuzzyCLIPS. Publications. Home Page of Geoffrey Hinton. I now work part-time for Google as a Distinguished Researcher and part-time for the University of Toronto as a Distinguished Emeritus Professor.

Home Page of Geoffrey Hinton

For much of the year, I work at the University from 9.30am to 1.30pm and at the Google Toronto office at 111 Richmond Street from 2.00pm to 6.00pm. I also spend several months per year working full-time for Google in Mountain View, California. Check out the new web page for Machine Learning at Toronto Information for prospective students: I will not be taking any more graduate students, visiting students, summer students or visitors, so please do not apply to work with me.

News Results of the 2012 competition to recognize 1000 different types of object How George Dahl won the competition to predict the activity of potential drugs How Vlad Mnih won the competition to predict job salaries from job advertisements How Laurens van der Maaten won the competition to visualize a dataset of potential drugs Basic papers on deep learning. Systems - Background.

In the past years a new aspect of brain research received more and more attention.

Systems - Background

"Computational Neuroscience" is not so much about the biological and biochemical characteristics of neurons as about their computational logistics. Very ambitious projects like Henry Markram's Blue Brain Project try to disclose the brains functioning by reconstructing it at the synapse-level in the form of a computer model.

The Blue Brain tries to model what is called a cortical column, a repetitive structure observed in all mammal brains. These columns were first described by Vernon B. Mountcastle as "Hypercolumns". During its evolution the neocortex was heavily driven by the needs of the visual system. The fundamental concept behind the CEPT-Retina consists in converting the symbolic representation of language into a SDR form so that it becomes numerically computable. An excellent overview of the potential of the word-space model is given in Magnus Sahlgren's dissertation named The Word-Space Model. Development and Evolution of the Human Neocortex.

NuPIC Details. Konstanz Information Miner. Weka 3 - Data Mining with Open Source Machine Learning Software in Java. Weka is a collection of machine learning algorithms for data mining tasks.

Weka 3 - Data Mining with Open Source Machine Learning Software in Java

The algorithms can either be applied directly to a dataset or called from your own Java code. Weka contains tools for data pre-processing, classification, regression, clustering, association rules, and visualization. It is also well-suited for developing new machine learning schemes. Found only on the islands of New Zealand, the Weka is a flightless bird with an inquisitive nature. The name is pronounced like this, and the bird sounds like this. Weka is open source software issued under the GNU General Public License. BigML is Machine Learning for everyone.