Multi-object recognition by optimized hierarchical temporal memory network

• The proposed network was designed to multi-object recognition.
• Sparse representation was used to capture interesting feature points.
• Prediction space was introduced and used to classify the input patterns.
• A proposed network was designed to object recognition and location.

In this paper, hierarchical temporal memory network (HTM) was optimized for multi-object recognition. HTM is constructed by temporal module and spatial module, which is formulated by Hawkins and George in 2005 based on prediction theory. Multi-object recognition is a spatial pattern recognition task, so we reduction the temporal module of hierarchical temporal memory network and strengthen the spatial module. Furthermore, sparse representation method was used for capturing the convolution kernels in the network, which simulates the function of the retina cells of the eyes. Moreover, the prediction space is used in the network to accelerate pattern identification. Finally, a four-level network was designed and trained for locomotive object recognition, and the recognition rate is up to 91.4%.