10 April 2018 A new pattern associative memory model for image recognition based on Hebb rules and dot product
Author Affiliations +
Proceedings Volume 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017); 1061512 (2018) https://doi.org/10.1117/12.2302483
Event: Ninth International Conference on Graphic and Image Processing, 2017, Qingdao, China
Abstract
A great number of associative memory models have been proposed to realize information storage and retrieval inspired by human brain in the last few years. However, there is still much room for improvement for those models. In this paper, we extend a binary pattern associative memory model to accomplish real-world image recognition. The learning process is based on the fundamental Hebb rules and the retrieval is implemented by a normalized dot product operation. Our proposed model can not only fulfill rapid memory storage and retrieval for visual information but also have the ability on incremental learning without destroying the previous learned information. Experimental results demonstrate that our model outperforms the existing Self-Organizing Incremental Neural Network (SOINN) and Back Propagation Neuron Network (BPNN) on recognition accuracy and time efficiency.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Mingyue Gao, Mingyue Gao, Limiao Deng, Limiao Deng, Yanjiang Wang, Yanjiang Wang, } "A new pattern associative memory model for image recognition based on Hebb rules and dot product ", Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 1061512 (10 April 2018); doi: 10.1117/12.2302483; https://doi.org/10.1117/12.2302483
PROCEEDINGS
7 PAGES


SHARE
Back to Top