We discuss implementations of the Adaptive Resonance Theory (ART) on a serial machine. The standard formulation of ART, which was inspired by recurrent brain structures, corresponds to a recursive algorithm. This induces an algorithmic complexity of order O(N-2)+O(MN) in worst and average case, N being the number of categories, and M the input dimension. It is possible, however, to formulate ART in a non-recursive algorithm such that the complexity is of order O(MN) only.
机构:
Univ Paris 01, Sorbonne Grad Business Sch IAE, Paris, FranceUniv Paris 01, Sorbonne Grad Business Sch IAE, Paris, France
Brandouy, Olivier
Delahaye, Jean-Paul
论文数: 0引用数: 0
h-index: 0
机构:
Univ Lille 1, Lab Informat Fondamentale Lille, Villeneuve Dascq, FranceUniv Paris 01, Sorbonne Grad Business Sch IAE, Paris, France
Delahaye, Jean-Paul
Ma, Lin
论文数: 0引用数: 0
h-index: 0
机构:
Univ Lille 1, Ecol Univ Management, Villeneuve Dascq, FranceUniv Paris 01, Sorbonne Grad Business Sch IAE, Paris, France
Ma, Lin
Zenil, Hector
论文数: 0引用数: 0
h-index: 0
机构:
Univ Paris 1 Pantheon Sorbonne, IHPST, Paris, France
Univ Sheffield, Dept Comp Sci, Sheffield, S Yorkshire, EnglandUniv Paris 01, Sorbonne Grad Business Sch IAE, Paris, France
机构:
Chinese Acad Sci, Inst Software, State Key Lab Comp Sci, Beijing 100190, Peoples R ChinaChinese Acad Sci, Inst Software, State Key Lab Comp Sci, Beijing 100190, Peoples R China