Home Contact Us
Reference  
News  
Reference - Articles
Technologies/Disciplines

 
 Connectionism - Part 2
This article was published in Direct Access for Canada's Information Systems Professionals. Direct Access is published 25 times a year by Laurentian Technomedia Inc., a unit of larentian Publishing Group.

Prepared By Dr. Mir F. Ali

In the last issue, part 1 discussed the concepts of connectionist theory and Artificial Intelligence (AI). Part 2 discusses applications of the neural net plus a connectionist method to retrieve information in hyperdocuments.

Applications:
Applications selected for this article include Discrimination/Classification, Numeric-symbolic Interfaces, Signal and Image Processing, Hard Learning, and Associative Learning.

Discrimination/Classification:
Discrimination and classification represent the domain for which neural nets are the most used in the company. They are usually compared with standard numerical methods. Neural networks are fed with data coming from a signal processing stage and are therefore considered as a data analyzer. The following features are normally included in neural network applications:

  • Passive and active sonar recognition.
  • Passive sonar for transient noise analysis.
  • Aerial acoustic identification.
  • Identification and emission-mode recognition of transmitters.
  • Target and sources recognition, echoes filtering for radar.
  • Identification in IR images.
  • Identification of flight phases (helicopter and aircraft).
  • Identification of industrial pieces.

Numeric-symbolic Interfaces:
It can happen that between a low level signal-processing stage (numeric data) and a high-level decision-making stage (symbolic data) some parts are lacking. In such cases neural methods are used:

  • Symbolic extraction from time-frequency sonar data.
  • Shape description for sea mines.
  • Interpretation of aerial sciences.

Signal and Image processing:
Neural nets are used as low-level processors, dealing directly with row signal: Image processing- compression (video equipment), contour extraction and noise reduction in satellite images. Temporal regression analysis is financial markets. Demultiplexing in reconstruction of radar images.

Hard Learning:
The essence of much current work in connectionist systems relates to hard learning, which may by described as follows:
Certain stable patterns cannot be achieved in a net without the presence of intermediate nodes that are not clamped units. These are required because clamping would cause conflicts between the stable states; later clamps modifying the logic set up by earlier ones; and Learning is said to be hard because the function for the intermediate units is not distinctly stated by the described clamp patterns. This function is molded by some global training algorithm applied to all intermediate nodes, the object of which is to cause changes in the logic that supports the clamp.

Associative Learning:
A multilayered associative network is designed to perform a pattern on the output nodes whenever another particular pattern occurs on the input nodes. In general, the learning algorithms should allow arbitrary patterns on both the input and output nodes.

There are two types of associative learning - patterns association and auto-association. A pattern association is to build up an association between a set of patterns with another set of patterns. During training, selected patterns are presented to both input and output nodes.

The contents of the memory of the PLN Neurons are modified so that whenever a particular pattern reappears on the input nodes, the associated pattern will appear on the output nodes. There is usually a teacher input indicating the desired pattern association during the training.

Other applications:

  • Optimization - processor allocation in sonar systems.
  • Control - last landing phase of aircraft.
  • Data fusion - multi-localization for radar sources. Associative memories - undersea sources localization. Pattern matching - cartographic correlation.

A Connectionist Method to Retrieve In formation in Hyperdocuments: Hyperdocuments are nonlinear documents made of linked nodes. The content of each node is text. Picture, sound or some mix of these in a multimedia hyperdocuments. That makes a convenient and promising organization for rich classes of sets of documents used in an electronic encyclopedia, computer-aided learning, software documentation, multi-Author editing, etc.

The inherent linked structure of the hyperdocument provides the native basis for the user interface, by means of controlling the displayed part of sub graphs called browsers, and selecting a node just by clicking on its icon. But this enjoyed high degree of freedom has its drawbacks.

First, one user may get lost after some explorations are conducted; second, the information stored is split into many small units that one user must read in a given order to understand; and third, the actual needs of the user are not taken into account in the navigation support, so unskilled users are frequently puzzled.

There is one way to overcome the attributes of nodes and links in the hyperdocument. Petri nets were proposed in 1989 as a foundation of an ordered browsing mechanism. This way, everyone is easily compelled to pass through prerequisites before accessing a node with highly specialized content. Thus the rules are static, the graph is more complex and the user's needs and specific background are still ignored.

F. Biennier, J.M. Pinon, M. Guivarch and Insa de Lyon, in an article on the subject, described an approach that is known as augmented query system, which takes into account a distance between a Node Specialization Level and a Specialization Level Hoped by the User.

Nodes and tags (multimedia key works) form a neural network, together with the cells' activation rules and hypertext links.

User's Needs:
First, the needs of information are defined. The answer must correspond to the query and has to be understandable by the user and adapted to the time the user has. There are four parameters involved in this model: Definition of his aim by tags; interest level related to the available time; specialization level that the user is looking for; and path needed and context.

Query tags:
A query is made of tags. The information retrieval systems are based either on Boolean or Vectorial models. A Boolean query is a Boolean expression of tags. In this model, the system answers cannot be ranked and there is quite a big problem of noise and silence.

Adaptations of this model allow the user to assign weights to the tags. The Vectorial model uses weighted tags. Thus the system answers may be ranked, but the query definition is quite difficult for a non-specialist.

A Vectorial query system and an inductive process are adopted in this model. The Vectorial query system uses a friendly man/machine interface, in which the user defines, for each tag selected, a weight in a graduate scale. The choice of tags is also helped by the use of a thesaurus.

Understanding Problems:
In fact, the problem is not only to find information that fits the query, but also to find information the user can understand. That is why the Specialization Level Hoped by the User and the Node Specialization Level are adapted in this model.

The Author of the node defines the Node Specialization Level. For the first access, the user defines the specialization level he or she is looking for, but he or she can modify it dynamically by reading other nodes.

Reading and browsing a hyperdocument supposes that the system gives the user an entry point and a path to guide his browsing activity. Building a path allows us to take the prerequisites into account dynamically and to use the proximity relationships between nodes.

The Neural Network:
A connectionist approach is used to implement this model. The neural network selected for this model, uses bi-directional links between cells. Cells represent either tags, or nodes of the hyperdocument. The weights of the links represent the measures of the power of content by a tag (for the reverse links).

An epigenetic network that can model thesaurus relationships is used in this model. The weights of the new links are computed using the old network structure. The relationships between tags are sought with an analysis of the network structure and specifically on shared contents. A tool is provided to help the designer toward this analysis.

In some sense, traditional bases of linear documents may be considered as hyperdocuments, thanks to links between documents or parts of the same document. That is why the hyperdocument approach may be used in many organizations.

The Future:
Igor Aleksander, in his book Neural Computing Architectures, addressed the question: What is the ultimate neural computing architecture of the future likely to be? Neural computing of ht future is not likely to be a replacement of conventional computing and AI programs, but rather is likely to form a complementary technology. It would border on the silly to create with difficulty neural computations that can be performed with ease through conventional methods.

The key issue, however, is that the two methods must be able to exit under the same roof. So the ultimate challenge for experts in computer architecture is to exploit the two technologies within the box, while presenting a single, flexible interface to the user.

Return to
Articles


Copyright 2003 - Automated Information Management Corporation