STATISTICA Automated Neural Networks (SANN)

Category Intelligent Software>Neural Network Systems/Tools

Abstract STATISTICA Automated Neural Networks (SANN) is one of the most advanced and best performing neural network applications on the market.

It offers numerous unique advantages and will appeal Not only to neural network (NN) experts (by offering them a wide selection of network types and training algorithms), but also to new users in the field of neural computing (via the unique Automated Network Search, a tool that guides the user through the necessary procedures for creating neural networks).

SANN features/capabilities include:

1) SANN -- Tackling the Real Issues in Neural Computing - Using NNs involves more than simply feeding data to a NN.

SANN has the functionality to assist you through the critical design stages, including Not only state-of-the-art NN Architectures and Training Algorithms, but also innovative new approaches to 'network architecture' design by using specific and meaningful ‘error functions’ that allow the interpretation of the output results.

Moreover, software developers and those users who experiment with customized applications will appreciate the fact that once your prototyping experiments are completed using SANN' simple and intuitive user interface, NNs analyses can be incorporated in custom applications by using either the STATISTICA library of COM functions that fully expose all functionality of the program or by using the C/C++ code generated by the program to aid in the deployment of fully trained networks.

2) Input Data -- SANN is fully integrated with the STATISTICA system, so a large selection of tools for editing (preparing) data for analyses is available (transformations, case selection conditions, data verification tools, etc.).

The program can be "connected" to remote databases via the tools for in-place-database processing, or it can be linked to active data so that models are retrained or applied (e.g., to compute predicted values or classifications) Automatically every time the data change.

3) Data Scaling and Nominal Value Preparation -- SANN includes Automated data scaling for both inputs and outputs; there is also Automated recoding of Nominal valued variables (e.g., Sex = {Male, Female}), including one-of-N encoding.

SANN also has facilities to handle missing data. There are special data preparation and interpretation facilities for use with Time Series. A large number of relevant tools are also included in STATISTICA.

For classification problems, SANN assigns cases to class memberships and interprets network outputs as true probabilities. In combination with SANN's specialized Softmax activation function and cross-entropy error functions, this supports a principled, probabilistic approach to classification.

4) Selecting a NN Model, NN Ensembles -- The Automated Network Search (ANS) is available to Automatically search through numerous network architectures of varying complexities; (see below).

SANN supports the most important classes of NNs for real world problem solving, including:

The above architecture can be used for regression, classification, regression time series, classification time series, and cluster analysis.

In addition, ANS supports Ensembles networks formed from arbitrary (when meaningful) combinations of the network types listed above. Combining networks to form Ensemble predictions are particularly easy to use in SANN, especially for noisy or small datasets.

SANN contains numerous facilities to aid in selecting an appropriate network architecture. SANN's statistical and graphical feedback includes histograms, matrices and graphs of individual and overall case errors, summaries of classification/misclassification performance, and vital statistics such as regression correlation - all Automatically calculated.

For data visualization, SANN can also display scatter-plots and 3D response surfaces to help the user understand the network's "behavior."

SANN Automatically retains copies of the best networks, which can be retrieved at any time. The usefulness and predictive validity of the network can Automatically be assessed by including test and validation samples and by evaluating the size and efficiency of the network as well as the cost of misclassification.

SANN supports a number of network customization options. You can specify a linear output layer for networks used in (but Not restricted to) regression problems or Softmax activation functions for probability- estimation in classification problems.

Cross-entropy error functions, based on information-theory models, are also included, and there is a range of specialized activation functions, including Exponential, Tangent Hyperbolic, Logistic Sigmoid, and Sine functions for both hidden and output neurons.

5) The Automated Network Search (Automated evaluation and selection of multiple network architectures) -- Included with SANN is a tool that can Automatically evaluate a large number of different NN architectures of varying complexities, and select the best set of specific architectures for the problem at hand. It is known as the Automated Network Search (ANS).

This search includes network types, network sizes and architectures, activation functions, and error functions when appropriate.

6) Training a Neural Network -- SANN supports the best known state-of- the-art training algorithms.

SANN includes fast, second-order training algorithms: Conjugate Gradient Descent and BSFGS. There is also a memory-less version of BFGS to which SANN Automatically switches whenever the amount of memory on your computer is at critical levels.

SANN iterative training procedures are complemented by Automated tracking of both the training error and an independent testing error as training progresses. Training can be aborted at any point by the click of a button, and you can also specify 'Stopping Conditions' when training should be prematurely aborted. When training has finished, you can check performance against train, test, and validation samples.

SANN also includes a range of training algorithms for Cluster analysis, which is based on the well known Kohonen algorithm for self organizing feature maps.

7) Probing and Testing a Neural Network -- SANN uses a range of statistics and graphical facilities.

You may select multiple models (and ensembles), in which case, wherever possible, SANN will display any results generated in a comparative fashion (e.g. by plotting the response curves for several models on a single graph, or presenting the predictions of several models in a single spreadsheet).

All statistics are generated independently for the training, test, and validation samples or combinations of your choice.

Overall statistics calculated include mean network error, the so-called confusion matrix for classification problems (which summarizes correct and incorrect classification across all classes), and the correlation for regression problems - all Automatically calculated.

Kohonen networks include a Topological Map window, which enables you to visually inspect unit activations during data analysis.

8) Electronic Manual -- SANN includes a well-illustrated manual, with a comprehensive, conceptual introduction to Neural Networks (and tutorials), and extensive context sensitive Help accessible from every dialog.

System Requirements

Minimum

Recommended

Manufacturer

Manufacturer Web Site SANN

Price Contact manufacturer.

G6G Abstract Number 20404

G6G Manufacturer Number 102540