Journal
NEUROCOMPUTING
Volume 73, Issue 4-6, Pages 684-689Publisher
ELSEVIER SCIENCE BV
DOI: 10.1016/j.neucom.2008.11.033
Keywords
Neural network; Nonlinearity; Receptive field; Sparse coding; Recognition
Categories
Ask authors/readers for more resources
Some linear sparse coding models have been proposed for modeling responses in the early stage of the visual system, but nonlinear operations are ubiquitous in visual cortex. So we put forward an associative sparse coding neural network (ASCNN) with nonlinear response property in top-layer coding units. In our ASCNN model, the choices of sparseness function must correspond to the characters of activation function. This paper gives several reasonable and efficient methods for constructing sparseness functions and activation functions. Experiment on benchmark natural image dataset shows that our model can successfully simulate receptive field and nonlinear sparse response property of simple cells. Moreover, in two recognition tasks on face images and handwritten digits, experimental results show that our model works much better than linear sparse coding model (Sparsenet) by combining with linear neural network classifier. (C) 2009 Elsevier B.V. Ali rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available