Figure - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
The spiking neural network (SNN) exhibits distinct advantages in terms of low power consumption due to its event-driven nature. However, it is limited to simple computer vision tasks because the direct training of SNNs is challenging. In this study, we propose a hybrid architecture called the spiking fully convolutional neural network (SFCNN) to ex...
Context in source publication
Similar publications
In this paper a new method called SCLA which stands for Spiking based Cellular Learning Automata is proposed for a mobile robot to get to the target from any random initial point. The proposed method is a result of the integration of both cellular automata and spiking neural networks. The environment consists of multiple squares of the same size an...
A regime of coexistence of asynchronous and clustered dynamics is analysed for globally coupled homogeneous and heterogeneous inhibitory networks of quadratic integrate-and-fire (QIF) neurons subject to Gaussian noise. The analysis is based on accurate extensive simulations and complemented by a mean-field description in terms of low-dimensional ne...
In spiking neural networks (SNN), there are emerging security threats, such as adversarial samples and poisoned data samples, which reduce the global model performance. Therefore, it is an important issue to eliminate the impact of malicious data samples on the whole model. In SNNs, a naive solution is to delete all malicious data samples and retra...
Recent advancements in neuroscience research have propelled the development of Spiking Neural Networks (SNNs), which not only have the potential to further advance neuroscience research but also serve as an energy-efficient alternative to Artificial Neural Networks (ANNs) due to their spike-driven characteristics. However, previous studies often ne...
For processing streaming events from a Dynamic Vision Sensor camera, two types of neural networks can be considered. One are spiking neural networks, where simple spike-based computation is suitable for low-power consumption, but the discontinuity in spikes can make the training complicated in terms of hardware. The other one are digital Complement...
Citations
... In addition, the conversion method is difficult to be applied to deep SNN because the conversion error will accumulate layer by layer. To reduce the SNN latency, the surrogate gradient learning methods have been widely adopted in deep SNN in recent years [28][29][30][31][32][33][34][35]. For this method, the derivation of an approximate differentiable function was calculated to replace the derivation of the spiking event. ...
Spiking neural network (SNN) is a biologically-plausible model and exhibits advantages of high computational capability and low power consumption. While the training of deep SNN is still an open problem, which limits the real-world applications of deep SNN. Here we propose a deep SNN architecture named Spiking SiamFC++ for object tracking with end-to-end direct training. Specifically, the AlexNet network is extended in the time domain to extract the feature, and the surrogate gradient function is adopted to realize direct supervised training of the deep SNN. To examine the performance of the Spiking SiamFC++, several tracking benchmarks including OTB2013, OTB2015, VOT2015, VOT2016, and UAV123 are considered. It is found that, the precision loss is small compared with the original SiamFC++. Compared with the existing SNN-based target tracker, e.g., the SiamSNN, the precision (success) of the proposed Spiking SiamFC++ reaches 0.861 (0.644), which is much higher than that of 0.528 (0.443) achieved by the SiamSNN. To our best knowledge, the performance of the Spiking SiamFC++ outperforms the existing state-of-the-art approaches in SNN-based object tracking, which provides a novel path for SNN application in the field of target tracking. This work may further promote the development of SNN algorithms and neuromorphic chips.
This study explores the application of the fully convolutional network (FCN) algorithm to the field of meteorology, specifically for the short-term nowcasting of severe convective weather events such as hail, convective wind gust (CG), thunderstorms, and short-term heavy rain (STHR) in Gansu. The training data come from the European Center for Medium-Range Weather Forecasts (ECMWF) and real-time ground observations. The performance of the proposed FCN model, based on 2017 to 2021 training datasets, demonstrated a high prediction accuracy, with an overall error rate of 16.6%. Furthermore, the model exhibited an error rate of 18.6% across both severe and non-severe weather conditions when tested against the 2022 dataset. Operational deployment in 2023 yielded an average critical success index (CSI) of 24.3%, a probability of detection (POD) of 62.6%, and a false alarm ratio (FAR) of 71.2% for these convective events. It is noteworthy that the predicting performance for STHR was particularly effective with the highest POD and CSI, as well as the lowest FAR. CG and hail predictions had comparable CSI and FAR scores, although the POD for CG surpassed that for hail. The FCN model’s optimal performances in terms of hail prediction occurred at the 4th, 8th, and 10th forecast hours, while for CG, the 6th hour was most accurate, and for STHR, the 2nd and 4th hours were most effective. These findings underscore the FCN model’s ideal suitability for short-term forecasting of severe convective weather, presenting extensive prospects for the automation of meteorological operations in the future.
Information regarding newly added construction land can be extracted from high-resolution remote sensing images. The retrieval accuracy of land cover changes across the country has improved, and the illegal use of land is actively monitored. To address the imbalance between positive and negative training samples in extracting information regarding newly added construction land, a method for identifying newly added construction land by weakening the weight of negative samples was proposed. A focal loss function was used to weaken the negative samples’ weights and improve the overfitting U-net. Since the two parameters of the focal loss function are not independent of each other, they need to be selected at the same time. Therefore, this paper developed a formula for selecting the balance factor α based on a large number of experimental results. First, the GF-2 image was combined with the historical land change survey data and monitoring vector results to construct a dataset, and then the training dataset was input into a fully convolutional neural network (CNN) integrated with feature fusion and a focal loss function. Finally, the accuracy of the trained network model was verified. To demonstrate the applicability of the method of determining the parameters of the focal loss function, the validation set was divided into four subsets for accuracy verification. The experimental results showed that the F1-score of newly added construction land information extracted by this method reached 0.913, which is 0.078 and 0.033 higher than those of the U-net and the improved U-net. The parameters obtained by the method proposed in this study achieved the best results on the four verification sets, which shows that the method for extracting newly added construction land information and that for selecting parameters have strong applicability.
