IIIT Hyderabad Publications |
|||||||||
|
Optimal Spherical Separability: Artificial Neural NetworksAuthors: Garimella Ramamurthy,Ganesh Yaparla,Rhishi Pratap Singh Conference: International Work-Conference on Artificial Neural Networks (IWANN 2017) Date: 2017-06-14 Report no: IIIT/TR/2017/68 AbstractIn this research paper, the concept of hyper-spherical/hyper- ellipsoidal separability is introduced. Method of arriving at the optimal hypersphere (maximizing margin) separating two classes is discussed. By projecting the quantized patterns into higher dimensional space (as in en- coders of error correcting code), the patterns are made hyper-spherically separable. Single/multiple layers of spherical/ellipsoidal neurons are pro- posed for multi-class classification. An associative memory based on hyper-ellipsoidal neuron is proposed. Full paper: pdf Centre for Communications |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |