Basically it depends on what is your work in a neural network.
For Academic purposes where you can get some university support, Emergent is a good choice whereas for individual purpose there are various options available which are open source such as
It actually depends on what you want to achieve. For other programming languages, you can use the following below:
Java:
- neuroph (http://neuroph.sourceforge.net/) - if you only want to deal with neural networks
- weka (http://www.cs.waikato.ac.nz/ml/weka/) - as a lot of machine learning algorithms and I think it as 1 or 2 neural networks implementations, you can always extend by looking in the web (http://www.laps.ufpa.br/aldebaro/weka/index.html ; http://wekaclassalgos.sourceforge.net/ ; or use the package manager from weka 3.7 (developer version) )
C:
- FANN (http://leenissen.dk/fann/wp/ )- interesting, clean implementation and bindable to other languages (c++,c#,java,python,R,php) (http://leenissen.dk/fann/wp/language-bindings/)
Python:
- Pybrain (http://pybrain.org/pages/features) - I have only done some basic tests with it, but I found it simple and easy to use and build upon.
STATISTICA Automated Neural Networks (SANN) (http://www.statsoft.com/Products/STATISTICA/Automated-Neural-Networks). SANN is one of the best performing neural networks applications.
I am go with the researcher Mahmoud Omid answer as following:
Weka (http://www.cs.waikato.ac.nz/ml/weka/),
NeuroSolutions (http://www.neurosolutions.com/)
STATISTICA Automated Neural Networks (SANN) (http://www.statsoft.com/Products/STATISTICA/Automated-Neural-Networks). SANN is one of the best performing neural networks applications.
The compared to above thing weka is good my point of view.
SPSS and Statistica both have neural network tools. Output format of SPSS is quite descriptive, whereas Statistica provides better insights to what actually happens inside, rather than portraying it as a black box.