By Topic

IEEE Communications Magazine

Issue 11 • Date Nov. 1989

Filter Results

Displaying Results 1 - 8 of 8
  • Information theory, complexity and neural networks

    Publication Year: 1989, Page(s):25 - 28
    Cited by:  Papers (9)  |  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (493 KB)

    Some of the main results in the mathematical evaluation of neural networks as information processing systems are discussed. The basic operation of feedback and feed-forward neural networks is described. Their memory capacity and computing power are considered. The concept of learning by example as it applies to neural networks is examined.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural-style microsystems that learn

    Publication Year: 1989, Page(s):29 - 36
    Cited by:  Papers (4)  |  Patents (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1094 KB)

    The basic operation of biological and electronic (artificial) neural networks (NNs) is examined. Learning by NNs is discussed, covering supervised learning, particularly back-propagation, and unsupervised and reinforcement learning. The use of VLSI implementation to speed learning is considered briefly. Applications of neural-style learning chips to pattern recognition, data compression, optimizat... View full abstract»

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

    Publication Year: 1989, Page(s):37 - 40
    Cited by:  Papers (13)  |  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (487 KB)

    The ability of optical systems to provide the massive interconnections between processors required in most neural network models, which constitutes their chief advantage for such applications, is discussed, focusing on holography. Because of the essential nonlinearity of the holographic connections, nonlinear processing elements are needed to perform complex computations. The use of GaAs hybrid op... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Handwritten digit recognition: applications of neural network chips and automatic learning

    Publication Year: 1989, Page(s):41 - 46
    Cited by:  Papers (35)  |  Patents (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (694 KB)

    Two novel methods for achieving handwritten digit recognition are described. The first method is based on a neural network chip that performs line thinning and feature extraction using local template matching. The second method is implemented on a digital signal processor and makes extensive use of constrained automatic learning. Experimental results obtained using isolated handwritten digits take... View full abstract»

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

    Publication Year: 1989, Page(s):47 - 50
    Cited by:  Papers (400)  |  Patents (32)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2483 KB)

    The author extends a previous review and focuses on feed-forward neural-net classifiers for static patterns with continuous-valued inputs. He provides a taxonomy of neural-net classifiers, examining probabilistic, hyperplane, kernel, and exemplar classifiers. He then discusses back-propagation and decision-tree classifiers; matching classifier complexity to training data; GMDH (generalized method ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integration of acoustic and visual speech signals using neural networks

    Publication Year: 1989, Page(s):65 - 71
    Cited by:  Papers (59)  |  Patents (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (844 KB)

    Results from a series of experiments that use neural networks to process the visual speech signals of a male talker are presented. In these preliminary experiments, the results are limited to static images of vowels. It is demonstrated that these networks are able to extract speech information from the visual images and that this information can be used to improve automatic vowel recognition. The ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural networks for switching

    Publication Year: 1989, Page(s):72 - 81
    Cited by:  Papers (59)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (945 KB)

    The author argues that a strong impetus for using neural networks is that they provide a framework for designing massively parallel machines. He notes that the highly interconnected architecture of switching networks suggests similarities to neural networks. He presents two switching applications in which neural networks can solve the problems efficiently. He shows that a computational advantage c... View full abstract»

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

    Publication Year: 1989, Page(s):82 - 88
    Cited by:  Papers (7)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (953 KB)

    The capabilities of neural networks are discussed, and technologies and tools for implementing them are examined. Potential applications of neural networks to national defense are described. They are: analysis of data from high-data-rate sensors; sonar array processing; electronic intelligence gathering; battlefield surveillance, both radar and infrared; aircraft detection; and multisensor fusion.... View full abstract»

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

Aims & Scope

IEEE Communications Magazine, considered by most to be their most important member benefit, provides timely information on all aspects of communications: monthly feature articles describe technology, systems, services, market trends, development methods, regulatory and policy issues, and significant global events.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
Osman Gebizlioglu
Huawei Technologies