Models of parallel learning systems
Tzung‐Pei Hong, S. S. Tseng · 2002
The technique of parallel processing is applied to concept learning. The learning strategies can be divided into two classes: top-down learning and bottom-up learning. Based on the partition of learning tasks on the multiple processors and the principle of divide-and-conquer, respectively, two corresponding parallel learning models are proposed. It is shown that these two models can be easily embedded into two practical and commonly used architectures: the MIMD shared memory architecture and the SIMD shared memory architecture. The ID3 and the version space learning strategies are parallelized to show how a parallel top-down learning or a parallel bottom-up learning strategy can work well.>