Learn More
Despite the fact that many symbolic and connec-tionist (neural net) learning algorithms are addressing the same problem of learning from classified examples, very little Is known regarding their comparative strengths and weaknesses. This paper presents the results of experiments comparing the ID3 symbolic learning algorithm with the perceptron and(More)
  • Alan Gove, Stephen Grossbergy, Ennio Mingollaz
  • 1995
A neural network model is developed to explain how visual thalamocortical interactions give rise to boundary percepts such as illusory contours and surface percepts such as lled-in brightnesses. Top-down feedback interactions are needed in addition to bottom-up feedforward interactions to simulate these data. One feedback loop is modeled between lateral(More)
  • 1