| |
|
|
|
|
|
|
|
|
|
| NeuroSolutions |
|
|
|
|
|
|
| Level Summary |
|
|
| Topologies |
|
|
|
|
|
|
|
|
| Multilayer Perceptron (MLP) |
|
|
|
|
|
|
|
|
| Generalized Feedforward
Network |
|
|
|
|
|
|
|
|
| Modular Network |
|
|
|
|
|
|
|
|
| Jordan / Elman Networks |
|
|
|
|
|
|
|
|
| Self-Organizing Map (SOM) |
|
|
|
|
|
|
|
|
| Principal Component Analysis
(PCA) |
|
|
|
|
|
|
|
|
| Radial Basis Function (RBF) |
|
|
|
|
|
|
|
|
| Probabilistic Neural Network
(PNN) |
|
|
|
|
|
|
|
|
| General Regression Neural
Network (GRNN) |
|
|
|
|
|
|
|
|
| Neuro-Fuzzy Network (CANFIS) |
|
|
|
|
|
|
|
|
| Support Vector Machine
Network |
|
|
|
|
|
|
|
|
| Hopfield Network |
|
|
|
|
|
|
|
|
| Time Delay Neural Network
(TDNN) |
|
|
|
|
|
|
|
|
| Time-Lag Recurrent Network
(TLRN) |
|
|
|
|
|
|
|
|
| General Recurrent Network |
|
|
|
|
|
|
|
|
| Maximum Number of Inputs / Outputs / Neurons
Per Layer |
50 |
500 |
Unlimited |
|
| Maximum Number
of Hidden Layers |
|
2 |
6 |
Unlimited |
|
| Learning
Paradigms |
|
|
|
|
|
|
|
|
| Backpropagation |
|
|
|
|
|
|
|
|
| Unsupervised
Learning |
|
|
|
|
|
|
|
|
| • Hebbian
• Ojas • Sangers |
|
|
| • Competitive •
Kohonen |
|
|
| Recurrent Backpropagation |
|
|
|
|
|
|
|
|
| Backpropagation through time |
|
|
|
|
|
|
|
|
| Gradient Descent Methods |
|
|
|
|
|
|
|
|
| Step / Momentum |
|
|
|
|
|
|
|
|
| Delta Bar Delta |
|
|
|
|
|
|
|
|
| Quickprop |
|
|
|
|
|
|
|
|
| Conjugate Gradient |
|
|
|
|
|
|
|
|
| Levenberg-Marquardt |
|
|
|
|
|
|
|
|
| Advanced Features |
|
|
|
|
|
|
|
|
| Exemplar Weighting |
Ü Improved training for data with unequal
class distribution |
|
|
|
|
|
|
|
| Macros / OLE Automation |
Ü API to Automate and control NeuroSolutions |
|
|
|
|
|
|
|
| Sensitivity Analysis |
Ü Technique to determine the most
influential inputs |
|
|
|
|
|
|
|
| Genetic Optimization |
Ü Intelligent searching for the best
parameters and inputs |
|
|
|
|
|
|
|
|
| Iterative Prediction |
Ü Advanced method for time series prediction |
|
|
|
|
|
|
|
| ANSI C++ Source Code
Generation |
|
|
|
|
|
|
|
|
| • Embed neural networks into your own applications |
|
|
| • Train neural networks on faster computers |
|
|
| User-defined Neural Components
(using DLLs) |
|
|
|
|
|
|
|
|
| •
Nonlinearities •
Interconnections •
Learning Rules |
|
| •
Error Criteria •
Input/Output •
Memory Structures |
|
|
|
|
|
|
|
|
|
|
|
|
Products
