The Spiking Neural Network (SNN), as one of the biologically inspired neural network infrastructures, has drawn increasing attention recently. It adopts binary spike activations to transmit information, thus the multiplications of activations and weights can be substituted by additions, which brings high energy efficiency. However, in the paper, we theoretically and experimentally prove that the binary spike activation map cannot carry enough information, thus causing information loss and resulting in accuracy decreasing. To handle the problem, we propose a ternary spike neuron to transmit information. The ternary spike neuron can also enjoy the event-driven and multiplication-free operation advantages of the binary spike neuron but will boost the information capacity. Furthermore, we also embed a trainable factor in the ternary spike neuron to learn the suitable spike amplitude, thus our SNN will adopt different spike amplitudes along layers, which can better suit the phenomenon that the membrane potential distributions are different along layers. To retain the efficiency of the vanilla ternary spike, the trainable ternary spike SNN will be converted to a standard one again via a re-parameterization technique in the inference. Extensive experiments with several popular network structures over static and dynamic datasets show that the ternary spike can consistently outperform state-of-the-art methods. Our code is open-sourced at https://github.com/yfguo91/Ternary-Spike.

Multidrug-resistance (MDR) Pseudomonas aeruginosa (P. aeruginosa) is a lethal gram-negative pathogen causing hospital-acquired and ventilator-associated pneumonia, which is difficult to treat. Our previous studies confirmed that baicalin, an essential bioactive component in Scutellaria baicalensis Georgi, exhibited anti-inflammatory effects in an acute pneumonia rat model induced by MDR P. aeruginosa. However, this effect of baicalin in constrast its low bioavailability, and its mechanism of action is still unknown. Thus, this study investigated whether the therapeutic effects of baicalin against MDR P. aeruginosa acute pneumonia are owing to the regulation of gut microbiota and their metabolites using pyrosequencing of the 16S rRNA genes in rat feces and metabolomics. As a result, baicalin attenuated the inflammation by acting directly on neutrophils and regulated the production of the inflammatory cytokines TNF-α, IL-1β, IL-6, and IL-10. The mechanisms were through down-regulation of TLR4 and inhibition of NF-κB. Furthermore, pyrosequencing of the 16S rRNA genes in rat feces revealed that baicalin regulated the composition of gut microbial communities. At the genus level, baicalin efficiently increased the abundance of Ligilactobacillus, Lactobacillus and Bacteroides, but decreased the abundance of Muribaculaceae and Alistipes. Further, arginine biosynthesis was analyzed as the core pathway regulated by baicalin via combination with predicting gut microbiota function and targeted metabolomics. In conclusion, this study has demonstrated that baicalin relieved inflammatory injury in acute pneumonia rat induced by MDR P. aeruginosa via arginine biosynthesis associated with gut microbiota. Baicalin could be a promising and effective adjunctive therapy for lung inflammation caused by MDR P. aeruginosa infection.

Zero-shot learning (ZSL) aims to leverage additional semantic information to recognize unseen classes. To transfer knowledge from seen to unseen classes, most ZSL methods often learn a shared embedding space by simply aligning visual embeddings with semantic prototypes. However, methods trained under this paradigm often struggle to learn robust embedding space because they align the two modalities in an isolated manner among classes, which ignore the crucial class relationship during the alignment process. To address the aforementioned challenges, this article proposes a visual–semantic graph matching net (VSGMN), which leverages semantic relationships among classes to aid in visual–semantic embedding. VSGMN uses a graph build net (GBN) and a graph matching net (GMN) to achieve two-stage visual–semantic alignment. Specifically, GBN first uses an embedding-based approach to build visual and semantic graphs in the semantic space and align the embedding with its prototype for first-stage alignment. In addition, to supplement unseen class relationships in these graphs, GBN also builds the unseen class nodes based on semantic relationships. In the second stage, GMN continuously integrates neighbor and cross-graph information into the constructed graph nodes and aligns the node relationships between the two graphs under the class relationship constraint. Extensive experiments on three benchmark datasets demonstrate that VSGMN achieves superior performance in both conventional and generalized ZSL (GZSL) scenarios. The implementation of our VSGMN and experimental results are available at github: https://github.com/dbwfd/VSGMN.