Search Constraints

Start Over
Filtering by: Subject Computer networks Remove constraint Subject: Computer networks Academic Affiliation Computer Science Remove constraint Academic Affiliation: Computer Science Subject Neural networks (Computer science) Remove constraint Subject: Neural networks (Computer science)

Search Results

  • An implementation and initial test of generalized radial basis functions

    Creator:
    Wettschereck, Dietrich
    Abstract:
    Generalized Radial Basis Functions were used to construct networks that learn input-output mappings from given data. They are developed out of a theoretical framework for approximation based on regularization techniques and represent a class of three-layer networks similar to backpropagation networks with one hidden layer. A network using Gaussian base...
    Resource Type:
    Masters Thesis
    Full Text:
    Science in Computer Science presented on June 27.1990. Title: An Implementation and Initial Test of

  • Representations and algorithms for efficient inference in Bayesian networks

    Creator:
    Takikawa, Masami
    Abstract:
    Bayesian networks are used for building intelligent agents that act under uncertainty. They are a compact representation of agents' probabilistic knowledge. A Bayesian network can be viewed as representing a factorization of a full joint probability distribution into the multiplication of a set of conditional probability distributions. Independence of causal...
    Resource Type:
    Dissertation
    Full Text:
    in Computer Science presented on October 15, 1998. Title: Representations and Algorithms for

  • Attentional flow networks : a real-time adaptive display technique

    Creator:
    Bible, John
    Abstract:
    Graphics resource allocation has often existed on the periphery of graphics research, taking second place to faster or more realistic algorithms for global illumination and modeling. Most research has focused on generating sets of images that best match the effects one might see in photographs. While this approach works well...
    Resource Type:
    Masters Thesis
    Full Text:
    for the computer-controlled actors, check for collisions, update the world, and perform network

  • Variations on ID3 for text-to-speech conversion

    Creator:
    Hild, Hermann
    Abstract:
    Summary of results. After implementing the plain ID3 algorithm, I experimented with various modifi cations. Two improvements of the process of finding a legal phoneme/stress could be made by using statistical information about the letter to phoneme/stress-mapping in the training set. Adding the CHI-SQUARE test to the ID3 algorithm was...
    Resource Type:
    Capstone Project
    Full Text:
    . In 1986 T. Sejnowski and C.R. Rosenberg presented a Neural Network that could learn to pronounce