作者：
Jerez, JMAtencia, MVico, FJUniv Malaga
Escuela Tecn Super Ingn & Informat Dept Lenguajes & Ciencias Computac E-29071 Malaga Spain Univ Malaga
Escuela Tecn Super Ingn & Informat Dept Matemat Aplicada E-29071 Malaga Spain
This paper presents a learning rule, CBA, to develop oriented receptive fields similar to those founded in cat striate cortex. The inherent complexity of the development of selectivity in visualcortex has led most au...
详细信息
This paper presents a learning rule, CBA, to develop oriented receptive fields similar to those founded in cat striate cortex. The inherent complexity of the development of selectivity in visualcortex has led most authors to test their models by using a restricted input environment. Only recently, some learning rules (the PCA and the BCM rules) have been studied in a realistic visual environment. For these rules, which are based upon Hebbian learning, single neuron models have been proposed in order to get a better understanding of their properties and dynamics. These models suffered from unbounded growing of synaptic strength, which is remedied by a normalization process. However, normalization seems biologically implausible, given the non-local nature of this process. A detailed stability analysis of the proposed rule proves that the CBA attains a stable state without any need for normalization. Also, a comparison among the results achieved in different types of visual environments by the PCA, the BCM and the CBA rules is provided. The final results show that the CBA rule is appropriate for studying the biological process of receptive field formation and its application in image processing and artificial vision tasks.
visualcortex is able to process information in multiple pathways and integrate various forms of representations. This paper proposed a bio-inspired method that utilizes the line-segment-based representation to perfor...
详细信息
visualcortex is able to process information in multiple pathways and integrate various forms of representations. This paper proposed a bio-inspired method that utilizes the line-segment-based representation to perform a dedicated channel for the geometric feature learning process. The extracted geometric information can be integrated with the original pixel-based information and implemented on both the convolutional neural networks (SegCNN) and the stacked autoencoders (SegSAE). Segment-based operations such as segConvolve and segPooling are designed to further process the extracted geometric features. The proposed models are verified on the MNIST dataset, Caltech 101 dataset and QuickDraw dataset for image classification. According to the experimental results, the proposed models can facilitate the classification accuracies especially when the sizes of the training set are limited. Particularly, the method based on multiple representations is found to be effective for classifying the hand-drawn sketches. (C) 2019 Elsevier B.V. All rights reserved.
暂无评论