No abstract

Automated construction of deep neural networks (DNNs) has become a research hot spot nowadays because DNN's performance is heavily influenced by its architecture and parameters, which are highly task-dependent, but it is notoriously difficult to find the most appropriate DNN in terms of architecture and parameters to best solve a given task. In this work, we provide an insight into the automated DNN construction process by formulating it into a multilevel multiobjective large-scale optimization problem with constraints, where the nonconvex, nondifferentiable, and black-box nature of this problem make evolutionary algorithms (EAs) to stand out as a promising solver. Then, we give a systematical review of existing evolutionary DNN construction techniques from different aspects of this optimization problem and analyze the pros and cons of using EA-based methods in each aspect. This work aims to help DNN researchers to better understand why, where, and how to utilize EAs for automated DNN construction and meanwhile, help EA researchers to better understand the task of automated DNN construction so that they may focus more on EA-favored optimization scenarios to devise more effective techniques.

No abstract

The LaAlO3∕BaTiO3 artificial superlattices were fabricated on (001)-oriented Nb-doped SrTiO3 substrates by laser molecular-beam epitaxy. The structures of the superlattice were analyzed by normal θ-2θ scan mode x-ray diffraction analysis, high-resolution reciprocal space mapping measurement, and x-ray reflectivity measurement. The use of a LaAlO3 cap layer could effectively reduce dislocation formation at the interface, which released the strain induced by the lattice misfit between the sublayers. The surface and interface were also smoothed by the use of a LaAlO3 cap layer. Therefore, the strain was maintained in the film and the ferroelectric property of the superlattice was significantly enhanced.

No abstract