The electromyogram(EMG) pattern recognition is essential for a motion generation of hand prosthesis. A new EMG pattern recognition method is based on the Hierarchical Temporal Memory(HTM) algorithm which is originally devised for image pattern recognition. In the modified HTM algorithm, a simplified two-level structure with spatial pooler, temporal pooler, and supervised mapper is used for efficient learning and classification of the EMG signals. To enhance the recognition performance, the category information is utilized not only in the supervised mapper but in the temporal pooler. The experimental results show that the ten hand motions are successfully classified and recognized.