PROJECT TITLE :
Distance-based large margin classifier suitable for integrated circuit implementation
A new learning method for classification issues that's suitable for integrated circuit implementation is presented. The method, that outperforms current approaches in many information sets, is predicated on a structural description of the learning set represented by a planar graph. The final classification operate consists of a hierarchical mixture of local consultants, that yields a large margin classifier for the full learning set. Since it is primarily based solely on distance calculations, on-chip learning can conjointly be executed. The tactic is also acceptable for on-line and incremental learning, since model parameters are obtained directly from the info set, without would like of user interaction for learning.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here