Now showing items 382-384 of 1835

    • A Formulation for Active Learning with Applications to Object Detection 

      Sung, Kah Kay; Niyogi, Partha (1996-06-06)
      We discuss a formulation for active example selection for function learning problems. This formulation is obtained by adapting Fedorov's optimal experiment design to the learning problem. We specifically show how to ...
    • Forecasting Global Temperature Variations by Neural Networks 

      Miyano, Takaya; Girosi, Federico (1994-08-01)
      Global temperature variations between 1861 and 1984 are forecast usingsregularization networks, multilayer perceptrons and linearsautoregression. The regularization network, optimized by stochasticsgradient descent associated ...
    • The Quadric Reference Surface: Theory and Applications 

      Shashua, Amnon; Toelg, Sebastian (1994-06-01)
      The conceptual component of this work is about "reference surfaces'' which are the dual of reference frames often used for shape representation purposes. The theoretical component of this work involves the question ...