Notes

Recommendations utilized: Sample Management.
Deep neural networks (DNNs) have enabled impressive breakthroughs in various artificial intelligence (AI) applications recently due to its capability of learning high-level features from big data. However, the current demand of DNNs for computational resources especially the storage consumption is growing due to that the increasing sizes of models are being required for more and more complicated applications. To address this problem, several tensor decomposition methods including tensor-train (TT) and tensor-ring (TR) have been applied to compress DNNs and shown considerable compression effectiveness. see more In this work, we introduce the hierarchical Tucker (HT), a classical but rarely-used tensor decomposition method, to investigate its capability in neural network compression. We convert the weight matrices and convolutional kernels to both HT and TT formats for comparative study, since the latter is the most widely used decomposition method and the variant of HT. We further theoretically and experimentally discover that the HT format has better performance on compressing weight matrices, while the TT format is more suited for compressing convolutional kernels. Based on this phenomenon we propose a strategy of hybrid tensor decomposition by combining TT and HT together to compress convolutional and fully connected parts separately and attain better accuracy than only using the TT or HT format on convolutional neural networks (CNNs). Our work illuminates the prospects of hybrid tensor decomposition for neural network compression.Object detectors have improved in recent years, obtaining better results and faster inference time. However, small object detection is still a problem that has not yet a definitive solution. The autonomous weapons detection on Closed-circuit television (CCTV) has been studied recently, being extremely useful in the field of security, counter-terrorism, and risk mitigation. This article presents a new dataset obtained from a real CCTV installed in a university and the generation of synthetic images, to which Faster R-CNN was applied using Feature Pyramid Network with ResNet-50 resulting in a weapon detection model able to be used in quasi real-time CCTV (90 ms of inference time with an NVIDIA GeForce GTX-1080Ti card) improving the state of the art on weapon detection in a two stages training. In this work, an exhaustive experimental study of the detector with these datasets was performed, showing the impact of synthetic datasets on the training of weapons detection systems, as well as the main limitations that these systems present nowadays. The generated synthetic dataset and the real CCTV dataset are available to the whole research community.Polyacrylonitrile (PAN)/β-cyclodextrin (β-CD) composite nanofibrous membranes immobilized with nano-titanium dioxide (TiO2) and graphene oxide (GO) were prepared by electrospinning and ultrasonic-assisted electrospinning. Scanning electron microscopy (SEM), energy dispersive spectroscopy (EDS), transmission electron microscopy (TEM), and X-ray diffraction (XRD) confirmed that TiO2 and GO were more evenly dispersed on the surface and inside of the nanofibers after 45 min of ultrasonic treatment. Adding TiO2 and GO reduced the fiber diameter; the minimum fiber diameter was 84.66 ± 40.58 nm when the mass ratio of TiO2-to-GO was 82 (PAN/β-CD nanofibrous membranes was 191.10 ± 45.66 nm). Using the anionic dye methyl orange (MO) and the cationic dye methylene blue (MB) as pollutant models, the photocatalytic activity of the nanofibrous membrane under natural sunlight was evaluated. It was found that PAN/β-CD/TiO2/GO composite nanofibrous membrane with an 82 mass ratio of TiO2-to-GO exhibited the best degradation efficiency for the dyes. The degradation efficiency for MB and MO were 93.52 ± 1.83% and 90.92 ± 1.52%, respectively. Meanwhile, the PAN/β-CD/TiO2/GO composite nanofibrous membrane also displayed good antibacterial properties and the degradation efficiency for MB and MO remained above 80% after 3 cycles. In general, the PAN/β-CD/TiO2/GO nanofibrous membrane is eco-friendly, reusable, and has great potential for the removal of dyes from industrial wastewaters.The response of adult human bone marrow stromal stem cells to surface topographies generated through femtosecond laser machining can be predicted by a deep neural network. The network is capable of predicting cell response to a statistically significant level, including positioning predictions with a probability P less then 0.001, and therefore can be used as a model to determine the minimum line separation required for cell alignment, with implications for tissue structure development and tissue engineering. The application of a deep neural network, as a model, reduces the amount of experimental cell culture required to develop an enhanced understanding of cell behavior to topographical cues and, critically, provides rapid prediction of the effects of novel surface structures on tissue fabrication and cell signaling.Anxiety in social interactions is an important factor in cigarette use and nicotine dependence. Metacognitions about smoking have been found to predict smoking behavior and may help understand the relationship between anxiety in social interactions and nicotine dependence. In the current study, we evaluated the direct effect of anxiety in social interactions on nicotine dependence and its indirect effect through metacognitions (controlling for anhedonia and depression) in nicotine-dependent men (n = 388). Participants completed measures of anxiety in social interactions [the Social Interaction Anxiety Scale (SIAS)], anhedonia [the Snaith HamiltonPleasure Scale (SHAPS)], metacognitions about smoking [e.g., theMetacognitions aboutSmoking Questionnaire (MSQ)] nicotine dependence [the Fagerström Test for Nicotine Dependence (FTND)], and clinical factors related to smoking including depressive symptoms [e.g., the Beck Depression Inventory-II (BDI-II)]. As expected, after controlling for depressive symptoms and anhedonia, anxiety in social interactions indirectly affected nicotine dependence through negative metacognitions about smoking, but not positive metacognitions. These findings are discussed in relation to the metacognitive model of addictive behaviors.
Homepage: https://www.selleckchem.com/products/phorbol-12-myristate-13-acetate.html