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%.

Tuning electronic and magnetic properties of GaN nanosheets by surface modifications and nanosheet thickness.

Density-functional theory calculations are performed to investigate the effects of surface modifications and nanosheet thickness on the electronic and magnetic properties of gallium nitride (GaN) nanosheets (NSs). Unlike the bare GaN NSs terminating with polar surfaces, the systems with hydrogenated Ga (H-GaN), fluorinated Ga (F-GaN), and chlorinated Ga (Cl-GaN) preserve their initial wurtzite structures and exhibit ferromagnetic states. The abovementioned three different decorations on Ga atoms are energetically more favorable for thicker GaN NSs. Moreover, as the thickness increases, H-GaN and F-GaN NSs undergo semiconductor to metal and half-metal to metal transition, respectively, while Cl-GaN NSs remain completely metallic. The predicted diverse and tunable electronic and magnetic properties highlight the potential of GaN NSs for novel electronic and spintronic nanodevices.