### About

The program *PNN* implements the algorithm proposed by Specht [1]. It is written in the R statistical language [2]. It solves a common problem in automatic learning. Knowing a set of observations described by a vector of quantitative variables, we classify them in a given number of groups. Then, the algorithm is trained with this dataset and should guess afterwards the group of any new observation. This neural network has the main advantage to begin generalization instantaneously even with a small set of known observations. The program is delivered with four functions — *learn*, *smooth*, *perf* and *guess* — and a dataset. The functions are documented with examples and provided with unit tests.

### Resources

The package is available at CRAN. Its current source code is available at Github. A manual of the functions -- *learn*, *smooth*, *perf* and *guess* -- is provided with examples. A lightning talk (abstract) have been presented at Rencontres R, 27-28/06/2013, Lyon, France. Several tutorials cover topics such as:

- How to install?
- How to use?
- How to optimize?
- How to evaluate the performance?
- Démonstration de la distribution des probabilités sur un jeu de données

### Author

### Licence

This program is released under the GNU Affero General public license.

### References

[1] | Specht, D. F. (1990). Probabilistic neural networks. Neural networks, 3(1):109–118. |

[2] | R Core Team (2012). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. ISBN 3-900051-07-0, http://www.R-project.org/. |