Search for: All records

Lightweight neural networks refer to deep networks with small numbers of parameters, which can be deployed in resource-limited hardware such as embedded systems. To learn such lightweight networks effectively and efficiently, in this paper we propose a novel convolutional layer, namely Channel-Split Recurrent Convolution (CSR-Conv), where we split the output channels to generate data sequences with length T as the input to the recurrent layers with shared weights. As a consequence, we can construct lightweight convolutional networks by simply replacing (some) linear convolutional layers with CSR-Conv layers. We prove that under mild conditions the model size decreases with the rate of O( 1 ). Empirically we demonstrate the state-of-the-art T2 performance using VGG-16, ResNet-50, ResNet-56, ResNet- 110, DenseNet-40, MobileNet, and EfficientNet as backbone networks on CIFAR-10 and ImageNet. Codes can be found on https://github.com/tuaxon/CSR Conv. 

The DNA phosphorothioate (PT) modification existing in many prokaryotes, including bacterial pathogens and commensals, confers multiple characteristics, including restricting gene transfer, influencing the global transcriptional response, and reducing fitness during exposure to chemical mediators of inflammation. While PT-containing bacteria have been investigated in a variety of environments, they have not been studied in the human microbiome. Here, we investigated the distribution of PT-harboring strains and verified their existence in the human microbiome. We found over 2000 PT gene-containing strains distributed in different body sites, especially in the gastrointestinal tract. PT-modifying genes are preferentially distributed within several genera, including Pseudomonas, Clostridioides, and Escherichia, with phylogenic diversities. We also assessed the PT modification patterns and found six new PT-linked dinucleotides (CpsG, CpsT, ApsG, TpsG, GpsC, ApsT) in human fecal DNA. To further investigate the PT in the human gut microbiome, we analyzed the abundance of PT-modifying genes and quantified the PT-linked dinucleotides in the fecal DNA. These results confirmed that human microbiome is a rich reservoir for PT-containing microbes and contains a wide variety of PT modification patterns.