## NNetSheet

** Category** Intelligent Software>Neural Network Systems/Tools

** Abstract** NNetSheet is a development system that creates
spreadsheet models of neural networks. These models are called
Neural Network Spreadsheets. NNetSheet-C implements the neural
network learning algorithms as dynamic link libraries (DLLs) -- C
programs dynamically linked to Microsoft Excel spreadsheets. To the
spreadsheet user, these neural network algorithms look like ordinary
spreadsheet formulas. Product helps you build applications for data
clustering, pattern recognition, and expert system rule generation.

All NNetSheet commands are configured in an easy-to-use Excel menu-bar that is integrated with all standard Excel commands and charting utilities. NNetSheet provides interactive help that takes you through the process of building neural network spreadsheet applications.

Additional features include:

Input/Output - NNetSheet inputs are any set of training examples that can be read by Microsoft Excel in any one of 13 formats. NNetSheet "outputs" are neural network formulas. The formulas access the NNetSheet Dynamic Link Libraries. To use the neural network, simply cut and paste the formulas to an application.

Size and Speed - The Excel spreadsheet limits the size of the training database to 32,787 rows and 256 columns. Training speed and neural network run-time speed depend on the hardware support for floating point computation.

NNetSheet neural network models and preprocessing utilities include:

- 1) Supervised Learning (for Prediction) - Perceptron Learning, Delta Rule, Generalized Delta Rule, Back Propagation (see detail info below).
- 2) Unsupervised Learning (for Clustering) - Hamming Metrics, Fuzzy Metrics, Hamming Histograms, Euclidean Metrics (see detail info below).
- 3) Data Preprocessing - Randomizing, Text Input, Scaling, Moving Averages (see detail info below).

NNetSheet supports the following models/algorithms and utilities:

- 1) Perceptron - Learns functions that map input vectors to discrete target values.
- 2) Delta Rule - Learns functions that map vectors to real target values.
- 3) Generalized Delta Rule - Learns functions that map intervals to interval targets.
- 4) Euclidean Clustering - Discovers data groupings based on Euclidean distances.
- 5) Hamming Clustering - Discovers data groupings of bit-vectors.
- 6) Fuzzy Hamming Clustering - Discovers data groupings of interval vectors.
- 7) Hamming Histogram - Discovers data correlations of bit-vectors.
- 8) Randomization - Improves convergence and separability by using nonlinear random inputs as a hidden layer.
- 9) Autoscaling - Improves convergence by normalizing inputs and outputs.
- 10) Representation of Text - Allows the NNetSheet-C algorithms to process text values, by mapping text to bit vectors.
- 11) Log Returns - A collection of time series analysis tools used for random walk statistics.
- 12) Moving Averages - A time series analysis tool used for smoothing and prediction.

Licenses - The basic single-user license includes the neural network algorithm development tools integrated with the Microsoft Excel user interface macros and dynamic link libraries; an on-line tutorial; a 120 Page Manual; and sample Applications. NNetSheet comes with E-mail Technical Support.

*System Requirements*

NNetSheet requires Microsoft Excel.

*Manufacturer*

- Inductive Solutions, Inc.
- 380 Rector Place, Suite 4A
- New York, New York 10280
- Email: info@inductive.com
- Telephone: +1 (212)945.0630
- Fax: +1 (212)945.0367

** Manufacturer Web Site** Inductive Solutions, Inc.

** Price** Student version $35; inquire for additional pricing.

** G6G Abstract Number** 20046

** G6G Manufacturer Number** 101400