Scheduled System Maintenance on May 29th, 2015:
IEEE Xplore will be upgraded between 11:00 AM and 10:00 PM EDT. During this time there may be intermittent impact on performance. We apologize for any inconvenience.
By Topic

Potentials, IEEE

Issue 3 • Date Oct. 1993

Filter Results

Displaying Results 1 - 8 of 8
  • Professionalism

    Publication Year: 1993 , Page(s): 5 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (344 KB)  

    The study of ethics concerns what is good and the behavioral patterns desired in a good person. This short analysis concerns itself first with general ethics and then more specifically with professional ethics. The paper focuses primarily on western civilization versions. Two major interpretations, total surrender and self-fulfilment, are discussed.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computing with neural networks

    Publication Year: 1993 , Page(s): 14 - 16
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (361 KB)  

    The resurgence of interest in neural networks is discussed. This interest is prompted by two facts. First, the nervous systems of simple animals can easily solve problems that are very difficult for conventional computers. Second, the ability to model biological nervous system functions using man-made machines increases understanding of that biological function. Two popular models of neural networks, the feedforward model and the feedback model, are described. Adaptation or learning, a major focus of neural network research, is detailed.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Perceptron-how this neural network model lets you evaluate Boolean functions

    Publication Year: 1993 , Page(s): 17 - 18
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (216 KB)  

    The author explores aspects of just what a neural network can do, by building a simple model that evaluates Boolean functions. The neural network model for the system that the author is building is one of the earliest: the perceptron, developed by Rosenblatt in the 1960s. The goal of the present work is to build a perceptron that can evaluate Boolean functions by learning the input patterns and the associated output. A major part of the process of building a neural net, the training of the network, is discussed. A wide variety of training algorithms have been developed. An analysis of the system is given, and limitations of the perceptron are described.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural systems: how the artificial version models itself after nature

    Publication Year: 1993 , Page(s): 19 - 20
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (217 KB)  

    The modeling of biological neurons is discussed, which leads to a system of nonlinear differential equations with several state variables for each neuron; this would be untenable in a computational application. A simple mathematical model is obtained retaining some essentials of real dynamic behavior. In order to make the network perform any task, it should be trained or it has to learn to solve the problem. The learning is inherent in biological systems. The learning procedures, supervised and unsupervised learning, are described. Current research on biological neural networks is discussed.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Genetic algorithms

    Publication Year: 1993 , Page(s): 21 - 24
    Cited by:  Papers (30)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (539 KB)  

    Genetic algorithms are exploratory procedures that are often able to locate near optimal solutions to complex problems. To do this, a genetic algorithm maintains a set of trial solutions, and forces them to evolve towards an acceptable solution. First, a representation for possible solutions must be developed. Then, starting with an initial random population and employing survival-of-the-fittest and exploiting old knowledge in the gene pool, each generation's ability to solve the problem should improve. This is achieved through a four-step process involving evaluation, reproduction, recombination, and mutation. As an application the author developed a genetic algorithm to train a product neural network for predicting the optimum transistor width in a CMOS switch, given the operating conditions and desired conductance.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Verbal requirements method

    Publication Year: 1993 , Page(s): 41 - 46
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (648 KB)  

    A definition of the verbal requirements method (VRM) is given. The VRM provides a natural language-like syntax to help software developers specify requirements easily. VRM was developed over a semester as a group project for a research course. The initial phase of the project was to survey existing specification languages and classify them on the basis of a fixed template. The latter phase of the research resulted in the actual specification language being developed. An example illustrates the use of the VRM for specifying a small real time system. The lack of constructs to specify software algorithms in terms of traditional conditional and looping structures enables specifiers to capture only the behavior of the system without reflecting the implementation details.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Programming transputers

    Publication Year: 1993 , Page(s): 47 - 49
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (385 KB)  

    The ease and difficulty of using Occam, a unique parallel programming language developed for transputers, is discussed. The transputer and the Occam language are described. The scope and limitations of Occam are detailed. Issues that are often sources of common mistakes and may cause problems in the design process are discussed.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Formal methods for system specification

    Publication Year: 1993 , Page(s): 50 - 52
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (505 KB)  

    Formal methods for system specification are described. The notation used in formal methods, called a formal specification language, is discussed. The deductive apparatus, an equally important component of a formal method, is also discussed.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.

Aims & Scope

IEEE Potentials is the magazine dedicated to undergraduate and graduate students and young professionals.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
David Tian
Carnegie Mellon University
david.tian@ieee.org