Title :
Learning concepts in parallel based upon the strategy of version space
Author :
Hong, Tzung-Pei ; Tseng, Shian-Shyong
Author_Institution :
Dept. of Comput. Sci., Chung-Hua Polytech. Inst., Hsinchu, Taiwan
fDate :
12/1/1994 12:00:00 AM
Abstract :
Applies the technique of parallel processing to concept learning. A parallel version-space learning algorithm based upon the principle of divide-and-conquer is proposed. Its time complexity is analyzed to be O(k log2n) with n processors, where n is the number of given training instances and k is a coefficient depending on the application domains. For a bounded number of processors in real situations, a modified parallel learning algorithm is then proposed. Experimental results are then performed on a real learning problem, showing that our parallel learning algorithm works, and being quite consistent with the results of theoretical analysis. We conclude that when the number of training instances is large, it is worth learning in parallel because of its faster execution
Keywords :
computational complexity; configuration management; generalisation (artificial intelligence); learning (artificial intelligence); parallel algorithms; application domains; bounded processor number; concept learning; divide-and-conquer method; generalization process; hypothesis; parallel version-space learning algorithm; specialization process; time complexity; training instances; Algorithm design and analysis; Artificial intelligence; Computer science; Concurrent computing; Costs; Councils; Information science; Learning; Parallel processing; Performance analysis;
Journal_Title :
Knowledge and Data Engineering, IEEE Transactions on