Flatness of the Energy Landscape for Horn Clauses

Abstract The Little-Hopfield neural network programmed with Horn clauses is studied. We argue that the energy landscape of the system, corresponding to the inconsistency function for logical interpretations of the sets of Horn clauses, has minimal ruggedness. This is supported by computer simulations. Keywords Little-Hopfield neural networks, Horn clauses, energy landscape, ruggedness

• Type: Journal
• Year: 2008
• Where: CORR
• Authors: Saratha Sathasivam, Wan Ahmad Tajuddin Wan Abdullah
• Keywords: CORR 2008, Education, Energy Landscape, Horn Clauses, Little-hopfield Neural Networks