dANN is an Artificial Intelligence and Artificial Genetics library targeted at employing conventional techniques as well as acting as a platform for research & development of novel techniques. As new techniques are developed and proven to be effective they will be integrated into the core library. It is currently written in Java, C++, and C#. However only the java version is currently in active development. If you want to obtain a version other than the java version you will need to get it directly from GIT.
Our intentions are two fold. First, to provide a powerful interface for programs to include conventional artificial neural network technology into their code. Second, To act as a testing ground for research and development of new AI concepts. We provide new AI technology we have developed, and the latest algorithms already on the market. In the spirit of modular programming the library also provides access to the primitive components giving you greater control over implementing your own unique AI algorithms. You can either let our library do all the work, or you can override any step along the way.
dANN currently implements several conventional as well as new algorithms inspired by its biological counterparts. The following is an incomplete list of some of the libraries features (based off the current development version, not released):
* Graph Theory o Search + Path Finding # A* # Dijkstra # Bellman-Ford # Johnson # Floyd-Warshall + Optimization # Hill Climbing Local Search o Graph Drawing + Hyperassociative Map # 3D Hyperassociative Map Visualization o Cycle Detection + Colored Depth First Search + Exhaustive Depth First Search o Minimal Spanning Tree Detection (MST) + Kruskal + Prim o Topological Sort Algorithm * Evolutionary Computing o Genetic Algorithms o Genetic Wavelets * Naive Classifier o Naive Bayes Classifier o Naive Fisher Classifier * Data Processing o Signal Processing + Cooley Tukey Fast Fourier Transform o Language Processing + Word Parsing + Word Stemming # Porter Stemming Algorithm * Graphical Models o Bayesian Networks + Dynamic Bayesian Networks # Hidden Markov Models * Baum–Welch Algorithm * Layered Hidden Markov Models * Hierarchical Hidden Markov Models * Artificial Neural Networks o Activation Function Collection o Backprop Networks + Feedforward Networks o Self Organizing Maps o 3D Network Visualization * Mathematics o Statistics + Markov Chains # Markov Chain Monte Carlo (Parameter Estimation) o Complex Numbers o N-Dimensional Vectors + 3D Vector Visualization o Linear Algebra + Cholesky Decomposition + Hessenberg Decomposition + Eigenvalue Decomposition + LU Decomposition + QR Decomposition + Singular Value Decomposition
We've included a package of examples. Some examples included are:
* 3-input XOR * 8 layer Hyperassociative Map * Neural Image Compression * 3D Color Maping to 2D/1D Space * Travelling Salesman Problem (TSP) * Wavelet Genetics * Microphone Spectrum Analyzer (FFT) * Path Finding Editable Grid
- Changes to previous version:
Please get the version in GIT only, the released version is old.
- BibTeX Entry: Download
- URL: Project Homepage
- Supported Operating Systems: Platform Independent
- Data Formats: None
- Tags: Neural Networks, Genetic Algorithms, Nn, Bayesian Networks, Ai, Ann, Genetic, Genetic Programming, Graph Theory, Hidden Markov Model, Markov Chain, Self Organizing Maps, Som
- Archive: download here
No one has posted any comments yet. Perhaps you'd like to be the first?
Leave a comment
You must be logged in to post comments.