			Universal Problem Solvers Products


(1) 	Multi-Pass Instance-Based Learning 
	(Pattern Recognition Software) is also available from:

DEMO available from:

	SimTel/win3/neurlnet/
	mpil10.zip      Multi-Pass Instance-Based Learning

Overview

MPIL is an instance-based learning system (instances are simply viewed as 
points in n-dimensional real-space with an associated neighborhood), which 
utilizes two models for creating neighborhoods.  The first model (i.e., MPIL-1) 
places a single neighborhood sphere (based on Euclidean distance measure) 
around an instance, and is in nature similar to the nearest neighbor 
classifier, except that it removes redundant instances.  The second model 
(i.e., MPIL-2) incorporates N radii (one for each input of an instance).  This 
model also supports knowledge acquisition in the form of rule extraction. 
In a sense, both approaches are similar to neural networks in that they exploit 
a very similar parallelism. MPIL represents a good alternative in cases were 
large amounts of data have to be learned and provides good  facilities for storage 
reduction.
   
Highlights:

	(1) Allows user to create an abstract instance representation of a training
	    set. 
	    
	(2) Provides features for Saving and Loading the abstract instance representation.
	
	(3) Supports two modes for instance-based learning: MPIL-1 and MPIL-2.
	
	(4) Supplies the user with the capability to test and classify new patterns.
	
	(5) Allows batch training and testing of a data set (i.e., n-fold crossvalidation) for
	    a user defined start partition size, end size, delta stepsize and parameter n.

	(6) Contains 21 example data sets.

	(7) Incremental Training

	(8) Can handle up to 2^16 training patterns (depended on available
	    system memory).
   
	Latest Version: MPIL v. 1.01
	Cost: US$20 + US$3 Shipping and Handling.
	PRICES SUBJECT TO CHANGE WITHOUT NOTIFICATION.
	Please, enquire for current price list prior to ordering (see address/e-mail below).
  


(1) 	Trans-Dimensional  Learning 
	(Pattern Recognition Software) 

DEMO available from:

	SimTel/win3/neurlnet/
	tdl103-1.zip     and tdl103-2.zip


Overview

The purpose of TDL is to provide users of neural networks with a specific 
platform to conduct pattern recognition tasks.  The system allows for the 
fast creation of automatically constructed neural networks. There is no need 
to resort to manually creating neural networks and twiddling with learning 
parameters.  Besides allowing the application user to automatically construct 
neural network for a given pattern recognition task, the system supports 
trans-dimensional learning.  Simply put, this allows one to learn various tasks 
within a single network, which otherwise differ in the  number of input stimuli 
and output responses utilized for describing them.  With TDL it is possible to
incrementally learn various pattern recognition tasks within a single coherent 
neural network structure.  Furthermore, TDL supports the use of semi-weighted 
neural networks, which represent a hybrid cross between standard weighted neural 
networks and weightless multi-level threshold units. Combining both can result in 
extremely compact network structures (i.e., reduction in connections and hidden units), 
and improve predictive accuracy on yet unseen patterns.

Highlights

	(1) Provides symbolic interface which allows the user to create:
	     
		(a) Input and output definition files.
		(b) Pattern files.
		(c) Help files for objects (i.e., inputs, input values, and outputs).

	(2) Supports categorization of inputs.  This allows the user to readily access inputs 
	     via a popup menu within the main TDL menu.  The hierarchical structure of the
	     popup menu is under the full control of the application developer (i.e., user).

	(3) Symbolic object manipulation tool:

		(a) Allows the user to interactively design the input/output structure of an 
		     application.  The user can create, delete, or modify inputs, outputs, 
		     input values, and categories.
		(b) Furthermore, inputs and categories can be moved from one location 
		     to another.
		(c) Receive a quick overview of the hierarchical category structure.

	(4) Supports Rule representation:

		(a) Extends standard Boolean operators (i.e., and, or, not) to contain several 
		      quantifiers (i.e., atmost, atleast, exactly, between).  
		(b) Provides mechanisms for rule revision (i.e., refinement) and extraction.
		(c) Allows partial rule recognition. Supported are first- and best-fit.

	(5) Allows co-evolution of different subpopulations (based on type of transfer function
	     chosen for each subpopulation).

	(6) Provides three types of crossover operators: simple random, weighted and blocked.

	(7) Supports both one-shot as well as multi-shot learning.  Multi-shot learning allows 
	     for the incremental acquisition of different data sets.  A single expert network is 
	     constructed, capable of recognizing all the data sets supplied during learning. Quick
	     context switching between different domains is possible.

	(8) Two types of local learning rules are included: perceptron and delta.

	(9) Implements 5 types of unit transfer functions: simple threshold, sigmoid, 
	     sigmoid-squash, n-level threshold, new n-level-threshold.

	(10) Data sets can contain either binary or continuous inputs and outputs.

	(11) Automatically constructed networks can be either tested (i.e., measure performance 
	       accuracy) or used for classifying new patterns.

	(12) Batch training and testing both in one-shot and multi-shot mode is supported. 

	(13) Graphical interface allows user to view the construction of a network over time and
	       view the change in unit activation during testing or classification.  Obtain detailed
		information on individual network units (i.e., unit id, weights, connections,
		transfer functions, etc.).  In case of n-level threshold or new-n-level threshold functions
		the user can view the activation\output function. Using the network dependency option
		the user can also view subnetworks.

	(14) Over a dozen statistics are collected during various batch training sessions.  These can
		be viewed using the chart option.

	(15) On-line help is available.

	(16) Network and memory resouces can be viewed directly.

	(17) An 88 page on-line overview of TDL is provided.  

	(18) A DEMONSTRATION of TDL can be invoked when initially starting the program.


Latest Version: TDL v. 1.03
	Cost: US$20 + US$3 Shipping and Handling.
	PRICES SUBJECT TO CHANGE WITHOUT NOTIFICATION.
	Please, enquire for current price list prior to ordering (see address/e-mail below).

 
Contact:

	Surface mail:	Universal Problem Solvers
			610 South Duncan Avenue
			Clearwater, FL 34616

	e-mail:		zlxx69a@prodigy.com

Mailing List: 

	If you would like to be informed when new products become available, please contact Universal 	Problem Solvers.  Please, state that you would like to be placed on a mailing list.

	
