연구의 선진화와 생산성 향상에
필요한 최적의 소프트웨어와 컨설팅을
공급하도록 노력하겠습니다.

NeuroSolutions for MATLAB

The NeuroSolutions for MATLAB neural network toolbox is a valuable addition to MATLAB's technical computing capabilities allowing users to leverage the power of NeuroSolutions inside MATLAB. The toolbox features 15 neural models, 5 learning algorithms and a host of useful utilities integrated in an easy-to-use interface, which requires 뱊ext to no knowledge?of neural networks to begin using the product.
The toolbox is also integrated with NeuroSolutions, which enables users to build custom networks in NeuroSolutions and use them inside MATLAB using the NeuroSolutions for MATLAB interface. The two products are available as a suite at a discounted price.
The free evaluation edition of NeuroSolutions for MATLAB includes several demos that will walk you step-by-step through the product. In addition, you can experiment with all of the features of this product using your own data. See how easy it is to solve your problems using neural networks inside the MATLAB environment.

Introduction

The NeuroSolutions for MATLAB neural network toolbox is a valuable addition to MATLAB뭩 technical computing capabilities allowing users to leverage the power of NeuroSolutions inside MATLAB. The toolbox features 15 neural models, 5 learning algorithms and a host of useful utilities that enable one to employ the power of neural networks to solve complicated real-world problems.
The toolbox is also integrated with NeuroSolutions. This enables users to build custom networks in NeuroSolutions and use them inside MATLAB using the NeuroSolutions for MATLAB interface. The two products are available as a suite at a discounted price.
The toolbox reduces the entire process of solving your problem with a neural network, into three short and simple steps.

Step 1: Creating a neural network

The easiest way to create a neural network using NeuroSolutions for MATLAB is to type the following command within the MATLAB interface.
  • >> mynet = nsnn;
The preceding command creates the default network, a one hidden layer Multi-Layer Perceptron (MLP), which is the most popular neural network among engineers and researchers worldwide. All the settings for the network are set to well-researched defaults, putting the neural network in a 밽ood-to-go?state after entering just one simple command.
SMART DEFAULTS
Other parameters that depend on your actual data are set when the data is passed to the train function (nsTrain). For example, the ideal number of neurons (processing elements) in the hidden layer of the neural network is computed from the data using a proprietary formula. Thus, the intricacies involved in setting up a neural network are automatically taken care of, allowing the user to concentrate on solving the problem at hand.
Here you have seen how to create the default MLP network. Many other neural networks and learning algorithms are available within NeuroSolutions for MATLAB. See the Product Summary for complete information.

Step 2: Training the Neural Network

The following command trains the neural network with your data.
  • >> mynet = nsTrain (mynet, x, y);
where, x is the input data and y is the desired data.
What do Input Data and Desired Data mean?
Cross validation can be performed without any additional effort by passing the cross validation data to the train function as well.
  • >> mynet = nsTrain (mynet, x, y, cv_x, cv_y);
where cv_x is the cross-validation input data and cv_y is the cross-validation desired data.
What is Cross Validation?
The learning curve and the output and desired plots can be seen with ease after training by setting their respective parameters to true.
  • >> mynet = nsnn;
  • >> mynet.learningCurve = true;
  • >> mynet.outputAndDesired = true;
  • >> mynet = nsTrain (mynet, inputData, desiredData);

Step 3: Testing and Utilizing the Neural Network

After training, the performance of the neural network model can be evaluated on a new out-of-sample testing data set.
  • >> [z_out, performance] = nsTest (mynet, z_in, z_desired);
  • >> performance
  • performance =
  • mse: 0.7316
  • nmse: 0.1728
  • correlation: 0.9095
  • percent_error: 13.1862
where z_in and z_desired represent the testing input and desired data respectively. z_out represents the output that the network actually produced when tested with z_in. The variable 봯erformance?/font> stores indicators comparing the network output z_out with the desired output z_desired.
Production Once you have created the network, trained and tested it to your satisfaction, the neural network is ready to be utilized in practice with production data.
  • >> p_out = nsProduction (mynet, p_in);
where p_in is the production input data and p_out is the network output for the production input data.
What is Production?

Easy-to-Use Interface

The NeuroSolutions neural network (nsnn) object created has many different parameters that can be edited. When the nsnn object variable name is displayed in the Matlab command line, every parameter is displayed with short comments that immediately explain the function of that parameter.


If there is any doubt in your mind as to what a parameter is actually used for, the help for any of the parameters can be obtained simply by typing ?help?after the parameter name.

Try out NeuroSolutions for MATLAB for Free

This brief tour has provided just a small glimpse into the overall capabilities of NeuroSolutions for MATLAB. The best way to find out more is to download the FREE evaluation version.

Feel free to contact one of our sales associates at 1-800-ND-IDEAS or sales@nd.com if you have any questions on the capabilities of the software or if you would like to place an order over the phone instead of using the secure online order form. Please note that if you should happen to change your mind within 30 days of purchase, you can return the software for a full refund (less shipping charges).
Thank you for taking the NeuroSolutions for MATLAB tour. Please browse through the rest of the site to learn more about all of NeuroDimension's products and services.

NeuroSolutions for MATLAB Product Summary

The NeuroSolutions for MATLAB neural network toolbox is a valuable addition for MATLAB users who want to leverage the power of NeuroSolutions inside MATLAB.
The toolbox features 15 neural models, 6 learning algorithms and a host of useful utilities that enables one to employ the power of neural networks to solve complicated real-world problems. All the capabilities are integrated in an easy-to-use interface, which requires 뱊ext to no knowledge?of neural networks to begin using. It allows you to concentrate on solving your problem using neural networks without having to spend many taxing hours perusing neural network literature and developing the algorithms yourself.
The toolbox is also integrated with NeuroSolutions. This enables users to build custom networks in NeuroSolutions, generate DLLs for those networks using the Custom Solution Wizard and then use those neural network DLLs inside MATLAB using the NeuroSolutions for MATLAB interface. The three products are available as a suite at a discounted price.
Easy-to-use interface
The functionality available in the toolbox is integrated in an easy-to-use interface that can be utilized by users with 뱊ext to no knowledge?/i> of neural networks. Users who are familiar with MATLAB would be able to pick up and use the entire package within a few minutes.
Features:
The toolbox features several variants of the following neural models:
  • Multi-Layer Perceptron
  • Generalized Feed Forward network
  • Modular neural network
  • Support Vector Machine
  • Partially Recurrent neural network
  • Fully Recurrent neural network
  • Time-Lag Recurrent neural network
The following 6 learning algorithms are featured along with the powerful Levenberg-Marquardt method:
  • Step
  • Momentum
  • Quickprop
  • Delta-Bar-delta
  • Conjugate Gradient
  • NEW Levenberg-Marquardt
Symbolic data translation allows for using textual data as inputs to a neural network. The symbolic data translation function comes paired with the inverse translation function that translates data back to symbols once all other tasks are completed. The image flattening utility flattens an image into a single row of data, so that it can be fed into a neural network. The performance indicators function reveals how well the neural network has trained with statistical indicators.
  • Symbolic data translation
  • Image flattening utility
  • Performance indicators
The NeuroSolutions for MATLAB neural network toolbox provides an quick, easy and powerful means to get neural networks to work for you. Download an evaluation copy today.