NeuroSolutions

NeuroSolutions
NeuroSolutions for Excel
Custom Solution Wizard
TradingSolutions
Genetic Server/ Library
Interactive Book
Complementary Products
Source Code License
Priority Support
Product Pricing

GUI
NeuralBuilder
Probing
Advanced Features
Developer Tools

Level Comparison
Educator
Users
Consultants
Professional
Developers Lite
Developers

Application Summaries
Neural Net Reference
Company History
Customer Quotes
Customer Forum
Mailing List
Reviews
Search
FAQ

What's new in NeuroSolutions 4?

NeuroSolutions 4 is a significant leap forward from NeuroSolutions 3. The two main goals in the development of this new version were to make the software easier to use and to add the latest in neural network technologies. Below is a summary of the features that were added to NeuroSolutions 4 to achieve these two goals.

Improved Ease of Use

NeuralExpert	The NeuralExpert asks you a series of questions about the type of problem you have and the location of the data. This wizard takes this information and intelligently builds the type and configuration of neural network to best solve your problem.
TestingWizard	After training a network, you will want to test the network performance on data that the network was not trained with. The TestingWizard automates this procedure by providing an easy way to produce the network output for out-of-sample data.
DataGraph	The DataGraph displays temporal data as a set of signal traces -- values (vertical axis) over time (horizontal axis). It is similar in functionality to the MegaScope, except it is much easier to use and includes labels on the X and Y axes so that you can get a better quantitative perspective on the probed data.
New Data Access Points	NeuroSolutions has always allowed you to post-process probed data using DLLs. Now several common calculations are built into the data access points: Confusion Matrix ROC Matrix AIC/MDL Correlation Coefficient Normalized Mean Squared Error Self-Organizing Map (SOM) metrics and visualization tools: Winning processing element Component plane - shows cluster characteristics Histogram of win frequencies U-matrix - shows distance between cluster centers Average quantization error

New Neural Network Technologies

Neuro- Fuzzy	The coactive neuro-fuzzy inference system (CANFIS) model integrates fuzzy inputs with a neural network to quickly solve poorly defined problems. Fuzzy inference systems are also valuable as they combine the explanatory nature of rules (membership functions) with the power of neural networks.
Genetic Optimization	A genetic algorithm can be used to optimize one or more parameters within the neural network in order to produce the lowest error. The most common parameters to optimize are the choice of inputs, the number of hidden units, the number of memory taps, and the learning rates. Many other network parameters are available for optimization.
SVM	The Support Vector Machine (SVM) model maps inputs to a high-dimensional feature space, and then optimally separates data into their respective classes by isolating those inputs that fall close to the data boundaries. They are especially effective in separating sets of data that share complex boundaries.
Conjugate Gradient	Conjugate gradient learning is a second-order training method that is an excellent trade-off between complexity and performance. Typically it trains faster and better (lower MSE) than standard backpropagation. In addition, it is completely parameterless -- no learning rates or momentum terms to adjust.
Teacher Forcing / Iterative Prediction	There are some time-series prediction problems that are best modeled using a method called teacher forcing. This specialized training algorithm feeds the predicted output back into the input in order to improve the accuracy of multi-step prediction. The predicted output of networks trained with teacher forcing is then obtained using iterative prediction.