Hervé Poulard

Learn More
A new algorithm for learning a threshold unit is proposed. The Barycentric Correction Procedure (BCP) is an eecient substitute for the Perceptron and its enhanced versions such as the Thermal Perceptron or the Pocket algorithm. Based on geometrical concepts, the BCP is much more eecient than the Perceptron for learning linearly separable mappings. To deal(More)
Among binary unit-based constructive algorithms, the Sequential Learning is particularly interesting for many reasons, the most significant one being its ability to treat real valued inputs without preprocessing. However, due to the construction process, the classical algorithms derived from the Perceptron cannot be used for learning each unit of the hidden(More)
  • 1