Efficient Resource-Aware Convolutional Neural Architecture Search for Edge Computing with Pareto-Bayesian Optimization.

With the development of deep learning technologies and edge computing, the combination of them can make artificial intelligence ubiquitous. Due to the constrained computation resources of the edge device, the research in the field of on-device deep learning not only focuses on the model accuracy but also on the model efficiency, for example, inference latency. There are many attempts to optimize the existing deep learning models for the purpose of deploying them on the edge devices that meet specific application requirements while maintaining high accuracy. Such work not only requires professional knowledge but also needs a lot of experiments, which limits the customization of neural networks for varied devices and application scenarios. In order to reduce the human intervention in designing and optimizing the neural network structure, multi-objective neural architecture search methods that can automatically search for neural networks featured with high accuracy and can satisfy certain hardware performance requirements are proposed. However, the current methods commonly set accuracy and inference latency as the performance indicator during the search process, and sample numerous network structures to obtain the required neural network. Lacking regulation to the search direction with the search objectives will generate a large number of useless networks during the search process, which influences the search efficiency to a great extent. Therefore, in this paper, an efficient resource-aware search method is proposed. Firstly, the network inference consumption profiling model for any specific device is established, and it can help us directly obtain the resource consumption of each operation in the network structure and the inference latency of the entire sampled network. Next, on the basis of the Bayesian search, a resource-aware Pareto Bayesian search is proposed. Accuracy and inference latency are set as the constraints to regulate the search direction. With a clearer search direction, the overall search efficiency will be improved. Furthermore, cell-based structure and lightweight operation are applied to optimize the search space for further enhancing the search efficiency. The experimental results demonstrate that with our method, the inference latency of the searched network structure reduced 94.71% without scarifying the accuracy. At the same time, the search efficiency increased by 18.18%.

Enantio- and Diastereoselective Nitro-Mannich Reaction of α-Aryl Nitromethanes with Amidosulfones Catalyzed by Phase-Transfer Catalysts.

A high-yield, highly diastereo- and enantioselective nitro-Mannich reaction of α-aryl nitromethanes with amidosulfones catalyzed by a novel chiral phase-transfer catalyst, bearing multiple H-bonding donors, derived from quinine was developed. A variety of α-aryl nitromethanes and amidosulfones were investigated; and the corresponding products were obtained in excellent yields with excellent diastereo- and enantioselectivities (up to 99% yield, > 99:1 dr and >99% ee). As a demonstration of synthetic utility, the resulting ß-nitroamines could be converted to corresponding meso-symmetric and optically pure unsymmetric anti-1,2-diarylethylenediamines.

Trabecular Bone Microarchitecture Evaluation in an Osteoporosis Mouse Model.

Bone microstructure refers to the arrangement and quality of bone tissue at the microscopic level. Understanding the bone microstructure of the skeleton is crucial for gaining insight into the pathophysiology of osteoporosis and improving its treatment. However, handling bone samples can be complex due to their hard and dense properties. Secondly, specialized software makes image processing and analysis difficult. In this protocol, we present a cost-effective and easy-to-use solution for trabecular bone microstructure analysis. Detailed steps and precautions are provided. Micro-CT is a non-destructive three-dimensional (3D) imaging technique that provides high-resolution images of trabecular bone structure. It allows for the objective and quantitative evaluation of bone quality, which is why it is widely regarded as the gold standard method for bone quality assessment. However, histomorphometry remains indispensable as it offers crucial cellular-level parameters, bridging the gap between two-dimensional (2D) and 3D assessments of bone specimens. As for the histologic techniques, we chose to decalcify the bone tissue and then perform traditional paraffin embedding. In summary, combining these two methods can provide more comprehensive and accurate information on bone microstructure.