Browsing by Author "Xu, Gang"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Open Access How good a shallow neural network is for solving non-linear decision-making problems(Springer, 2018-12-31) He, Hongmei; Zhu, Zhilong; Xu, Gang; Zhu, ZhenhuanThe universe approximate theorem states that a shallow neural network (one hidden layer) can represent any non-linear function. In this paper, we aim at examining how good a shallow neural network is for solving non-linear decision making problems. We proposed a performance driven incremental approach to searching the best shallow neural network for decision making, given a data set. The experimental results on the two benchmark data sets, Breast Cancer in Wisconsin and SMS Spams, demonstrate the correction of universe approximate theorem, and show that the number of hidden neurons, taking about the half of input number, is good enough to represent the function from data. It is shown that the performance driven BP learning is faster than the error-driven BP learning, and that the performance of the SNN obtained by the former is not worse than that of the SNN obtained by the latter. This indicates that when learning a neural network with the BP algorithm, the performance reaches a certain value quickly, but the error may still keep reducing. The performance of the SNNs for the two databases is comparable to or better than that of the optimal linguistic attribute hierarchy, obtained by a genetic algorithm in wrapper or in terms of semantics manually, which is much time-consuming.Item Open Access Recognition of speed signs in uncertain and dynamic environments(IOP Publishing: Conference Series, 2019-05-08) Zhu, Zhilong; Xu, Gang; He, Hongmei; Jiang, Juanjuan; Wang, TaoThe speed limit signs recognition directly affects the safety of autonomous vehicles. Vehicles are usually running in an uncertain and dynamic environment. The performance of the recognition system is affected by various factors such as the different sizes of pictures, illumination condition and position circumstances, which can lead to misclassification. This makes the speed sign recognition challengeable. To improve the recognition rate of the speed signs in such environments, this work firstly applies the method of the saliency target detection based on the background-absorbing Markov chain, to extract the node in an image, then uses SPP-CNN to classify the extracted nodes with ten-folder validation. The recognition rate is up to 9.32%, higher than that obtained directly by SPP-CNN working on raw dataset.