Title :
Abduction in Neuro Symbolic Integration
Author :
Sathasivam, Saratha
Author_Institution :
Sch. of Math. Sci., Univ. Sains Malaysia, Minden, Malaysia
Abstract :
Abduction is the process of proceeding from data describing a set of observations or events, to a set of hypotheses which best explains or accounts for the data. Most of the work on abduction has been done using a logical or a probabilistic approach. In this paper, we describe logic recognition as application of this abduction underlying logic to identify data sets of logical clauses that are having similar logic content. Abduction is used in recognition of similar logic content while evading differences in knowledge representations. We used Reverse Analysis method based on Hopfield network to capture the rules underlying in a database. Later, we used abduction technique for logic recognition in that database.
Keywords :
Hopfield neural nets; data analysis; inference mechanisms; knowledge representation; Hopfield network; abduction technique; knowledge representation; logical clause; neuro symbolic integration; reverse analysis method; similar logic content recognition; Algorithm design and analysis; Biological neural networks; Cognition; Data mining; Databases; Hopfield neural networks; Neurons; Hopfield; Reverse Analysis; abduction; logic;
Conference_Titel :
Bio-Inspired Computing: Theories and Applications (BIC-TA), 2011 Sixth International Conference on
Conference_Location :
Penang
Print_ISBN :
978-1-4577-1092-6
DOI :
10.1109/BIC-TA.2011.50