Constrain Bias Addition to Train Low-Latency Spiking Neural Networks.

In recent years, a third-generation neural network, namely, spiking neural network, has received plethora of attention in the broad areas of Machine learning and Artificial Intelligence. In this paper, a novel differential-based encoding method is proposed and new spike-based learning rules for backpropagation is derived by constraining the addition of bias voltage in spiking neurons. The proposed differential encoding method can effectively exploit the correlation between the data and improve the performance of the proposed model, and the new learning rule can take complete advantage of the modulation properties of bias on the spike firing threshold. We experiment with the proposed model on the environmental sound dataset RWCP and the image dataset MNIST and Fashion-MNIST, respectively, and assign various conditions to test the learning ability and robustness of the proposed model. The experimental results demonstrate that the proposed model achieves near-optimal results with a smaller time step by maintaining the highest accuracy and robustness with less training data. Among them, in MNIST dataset, compared with the original spiking neural network with the same network structure, we achieved a 0.39% accuracy improvement.

In Situ Irradiated X-Ray Photoelectron Spectroscopy Investigation on a Direct Z-Scheme TiO2 /CdS Composite Film Photocatalyst.

Inspired by nature, artificial photosynthesis through the construction of direct Z-scheme photocatalysts is extensively studied for sustainable solar fuel production due to the effectiveness in enhancing photoconversion efficiency. However, there is still a lack of thorough understanding and direct evidence for the direct Z-scheme charge transfer in these photocatalysts. Herein, a recyclable direct Z-scheme composite film composed of titanium dioxide and cadmium sulfide (TiO2 /CdS) is prepared for high-efficiency photocatalytic carbon dioxide (CO2 ) reduction. In situ irradiated X-ray photoelectron spectroscopy (ISI-XPS) confirms the direct Z-scheme charge-carrier migration pathway in the photocatalytic system. Furthermore, density functional theory simulation identifies the intrinsic cause for the formation of the direct Z-scheme heterojunction between the TiO2 and the CdS. Thanks to the significantly enhanced redox abilities of the charge carriers in the direct Z-scheme system, the photocatalytic CO2 reduction performance of the optimized TiO2 /CdS is 3.5, 5.4, and 6.3 times higher than that of CdS, TiO2 , and commercial TiO2 (P25), respectively, in terms of methane production. This work is a valuable guideline in preparation of highly efficient recyclable nanocomposite for photoconversion applications.