Multichannel spatio-temporal topographic processing for visual search and navigation

A Recurrent Fuzzy Coupled Cellular Neural Network System With Automatic Structure and Template Learning

“…The ordered set of equations, described in Section II in each layer, is summarized in (5)-(10). Our goal is to minimize the error function (4) where is the desired output, is the current output, and is . For each training data set, starting at the input nodes, a forward pass is used to compute the activity levels of all the nodes in the network to obtain the current output .…”

“…Besides some basic image processing tasks, the CNN has been used to mimic the local function of biological neural circuits, especially the human visual pathway system [3]. A current biological study [4] shows that mammalian visual systems process the world through a set of separate parallel channels. Each subchannel can be regarded as a unique CNN.…”

“…To solve this problem, the fuzzy inference system (FIS) can play an important role to integrate a set of CNNs into a system. To make a set of CNNs in parallel achieve higher level information processing, several integrated CNN systems are proposed [4]- [7]. They have two common characteristics.…”

New horizon for CNN: with fuzzy paradigms for multimedia

“…Besides some basic image processing tasks, the CNN has been used to mimic the local function of biological neural circuits, especially the human visual pathway system [3]. According to a current biological study [4], mammalian visual systems process the world through a set of separate parallel channels. As shown in Figure 2, each subchannel can be regarded as a unique CNN.…”

“…To make a set of CNNs in parallel achieve higher-level information processing, several integrated CNN systems were also proposed [4], [9]-- [11]. The common problem of these approaches is that the corresponding templates cannot be learned and the fuzzy rules must be obtained by domain experts.…”