Knowledge-guided Semantic Computing Network

Therefore, the existing models still need further improvement. Fortunately, the visual cognition process of human brain [9] provides a very good idea for this improvement. After visual information is transmitted to the brain via the eyes, it is processed by the human visual cortex. The visual cortex mainly includes the primary visual cortex (V1, also known as the striate cortex) and the extrastriate cortex (such as V2, V3, V4, V5, etc.). In 1962, Hubel and Wiesel [10] found that some cells in V1 only respond to bright or dark strips with special orientations and for each cell, there is an optimal position in which the cell reacts most strongly. Riesenhuber M et al [9] describe a new hierarchical model consistent with physiological data from inferior temporal cortex that accounts for this complex visual task and makes testable predictions. Matthew Lawlor et al points out that long-range horizontal connections among V1 cells enable V1 to respond to curvature [11]. Besides, Livingstone and Hubel [12] proposed that different types of V1 cells make up three different structures in V1, which respectively perceives and transmits the information about the color, the shape, the movement and stereoscopic vision to V2 and subsequent cells. During the whole human visual cognition process, visual information goes through two different visual pathways. One of them called'dorsal stream' leads to the parietal cortex for spatial vision (the information about'where'); another one called'ventral stream' leads to inferior temporal cortex for object vision (the information about'what') [13]. Areas along both pathways are hierarchical structures, such that low-level inputs are transformed into more useful representations through successive stages of processing. Abstract--It is very useful to integrate human knowledge and experience into traditional neural networks for faster learning speed, fewer training samples and better interpretability. However, due to the obscured and indescribable black box model of neural networks, it is very difficult to design its architecture, interpret its features and predict its performance. Inspired by human visual cognition process, we propose a knowledge-guided semantic computing network which includes two modules: a knowledge-guided semantic tree and a data-driven neural network.