Neural architecture search (NAS) has attracted increasing attention. In recent years,
search methods have been replaced by
search methods for higher search efficiency, but the latter methods often suffer lower instability. This article provides a literature review on these methods and owes this issue to the
. From this perspective, we summarize existing approaches into several categories according to their efforts in bridging the gap, and we analyze both advantages and disadvantages of these methodologies. Finally, we share our opinions on the future directions of NAS and AutoML. Due to the expertise of the authors, this article mainly focuses on the application of NAS to computer vision problems.
A global reference path generated by a path search algorithm based on a road-level driving map cannot be directly used to complete the efficient autonomous path-following motion of autonomous vehicles due to the large computational load and insufficient path accuracy. To solve this problem, this paper proposes a lane-level bidirectional hybrid path planning method based on a high-definition map (HD map), which effectively completes the high-precision reference path planning task. First, the global driving environment information is extracted from the HD map, and the lane-level driving map is constructed. Real value mapping from the road network map to the driving cost is realized based on the road network information, road markings, and driving behavior data. Then, a hybrid path search method is carried out for the search space in a bidirectional search mode, where the stopping conditions of the search method are determined by the relaxation region in the two search processes. As the search process continues, the dimension of the relaxation region is updated to dynamically adjust the search scope to maintain the desired search efficiency and search effect. After the completion of the bidirectional search, the search results are evaluated and optimized to obtain the reference path with the optimal traffic cost. Finally, in an HD map based on a real scene, the path search performance of the proposed algorithm is compared with that of the simple bidirectional Dijkstra algorithm and the bidirectional BFS search algorithm. The results show that the proposed path search algorithm not only has a good optimization effect, but also has a high path search efficiency.
The improvement of reservoir operation optimization (ROO) can lead to comprehensive economic benefits as well as sustainable development of water resources. To achieve this goal, an algorithm named wind-driven optimization (WDO) is first employed for ROO in this paper. An improved WDO(IWDO) is developed by using a dynamic adaptive random mutation mechanism, which can avoid the algorithm stagnation at local optima. Moreover, an adaptive search space reduction (ASSR) strategy that aims at improving the search efficiency of all evolutionary algorithms is proposed. The application results of the Goupitan hydropower station show that IWDO is an effective and viable algorithm for ROO and is capable of obtaining greater power generation compared to the classic WDO. Moreover, it is shown that the ASSR strategy can improve the search efficiency and the quality of scheduling results when coupled with various optimization algorithms such as IWDO, WDO and particle swarm optimization.
Nearly all motile organisms must search for food, often requiring multiple phases of exploration across heterogeneous environments. The fruit fly, Drosophila, has emerged as an effective model system for studying this behavior, however, little is known about the extent to which experiences at one point in their search might influence decisions in another. To investigate whether prior experiences impact flies’ search behavior after landing, I tracked individually labelled fruit flies as they explored three odor emitting but food-barren objects. I found two features of their behavior that are correlated with the distance they travel on foot. First, flies walked larger distances when they approached the odor source, which they were almost twice as likely to do when landing on the patch farthest downwind. Computational fluid dynamics simulations suggest this patch may have had a stronger baseline odor, but only ∼15% higher than the other two. This small increase, together with flies’ high olfactory sensitivity, suggests that perhaps their flight trajectory used to approach the patches plays a role. Second, flies also walked larger distances when the time elapsed since their last visit was longer. However, the correlation is subtle and subject to a large degree of variability. Using agent-based models, I show that this small correlation can increase search efficiency by 25-50% across many scenarios. Furthermore, my models provide mechanistic hypotheses explaining the variability through either a noisy or straightforward decision-making process. Surprisingly, these stochastic decision-making algorithms enhance search efficiency in challenging but realistic search scenarios compared to deterministic strategies.
With the construction and improvement of 5G infrastructure, more devices choose to access the Internet to achieve some functions. People are paying more attention to information security in the use of network devices. This makes lightweight block ciphers become a hotspot. A lightweight block cipher with superior performance can ensure the security of information while reducing the consumption of device resources. Traditional optimization tools, such as brute force or random search, are often used to solve the design of Symmetric-Key primitives. The metaheuristic algorithm was first used to solve the design of Symmetric-Key primitives of SKINNY. The genetic algorithm and the simulated annealing algorithm are used to increase the number of active S-boxes in SKINNY, thus improving the security of SKINNY. Based on this, to improve search efficiency and optimize search results, we design a novel metaheuristic algorithm, named particle swarm-like normal optimization algorithm (PSNO) to design the Symmetric-Key primitives of SKINNY. With our algorithm, one or better algorithm components can be obtained more quickly. The results in the experiments show that our search results are better than those of the genetic algorithm and the simulated annealing algorithm. The search efficiency is significantly improved. The algorithm we proposed can be generalized to the design of Symmetric-Key primitives of other lightweight block ciphers with clear evaluation indicators, where the corresponding indicators can be used as the objective functions.
Cell migration through extracellular matrices is critical to many physiological processes, such as tissue development, immunological response and cancer metastasis. Previous models including persistent random walk (PRW) and Lévy walk only explain the migratory dynamics of some cell types in a homogeneous environment. Recently, it was discovered that the intracellular actin flow can robustly ensure a universal coupling between cell migratory speed and persistence for a variety of cell types migrating in the in vitro assays and live tissues. However, effects of the correlation between speed and persistence on the macroscopic cell migration dynamics and patterns in complex environments are largely unknown. In this study, we developed a Monte Carlo random walk simulation to investigate the motility, the search ability and the search efficiency of a cell moving in both homogeneous and porous environments. The cell is simplified as a dimensionless particle, moving according to PRW, Lévy walk, random walk with linear speed-persistence correlation (linear RWSP) and random walk with nonlinear speed-persistence correlation (nonlinear RWSP). The coarse-grained analysis showed that the nonlinear RWSP achieved the largest motility in both homogeneous and porous environments. When a particle searches for targets, the nonlinear coupling of speed and persistence improves the search ability (i.e. find more targets in a fixed time period), but sacrifices the search efficiency (i.e. find less targets per unit distance). Moreover, both the convex and concave pores restrict particle motion, especially for the nonlinear RWSP and Lévy walk. Overall, our results demonstrate that the nonlinear correlation of speed and persistence has the potential to enhance the motility and searching properties in complex environments, and could serve as a starting point for more detailed studies of active particles in biological, engineering and social science fields.
With the development of measurement technology, the Flexible Measuring Arm (FMA) is widely used in quality test of automobile processing and industrial production. FMA is a kind of nonlinear system with many parameters. Low cost and efficient calibration method have become the focuses of attention. This article presents a fast calibration method for FMA based on an adaptive Genetic Algorithm (GA) just with several standard balls and a ball plate. It can greatly reduce the calibration cost than common external calibration method which needs high precision instruments and sensors. Firstly, the kinematic model of FMA is established by RPY theory. Secondly, the common GA is optimized and improved, and an adaptive mechanism is added to the algorithms which can realize the automatic adjustment of crossover and mutation operators. A Normalized Genetic Algorithm (NGA) with adaptive mechanism is proposed to complete the optimization calculation. It can improve the numbers of optimal individuals and the convergence speed. So, the search efficiency will be enhanced greatly. Finally, the Least square method (LSM), the General Genetic Algorithm (GGA), and the proposed NGA are respectively used to finish the calibration work. The compensation accuracy and the search efficiency with the above three different algorithms have been systematically analyzed. Experiment indicates that the performance of NGA is much better than LSM and GGA. The data also has proved that the LSM is suitable to complete optimization calculation for linear system. Its convergence stability is much poorer than NGA and GGA because of the ill-condition Jacobin matrix. GGA is easy to fall into local optimization because of the fixed operators. The proposed NGA obviously owns fast convergence speed, high accuracy and better stability than GGA. The position error is reduced from 3.17 to 0.5 mm after compensation with the proposed NGA. Its convergence rate is almost two time of GGA which applies constant genetic factors. The effectiveness and feasibility of proposed method are verified by experiment.
It is a well-documented phenomenon that individuals stop searching earlier than predicted by the optimal, risk-neutral stopping rule, leading to inefficient searches. Individuals' search behaviors during making investment decisions in financial markets can be easily affected by their peers. In this study, we designed a search game in a simplified experimental stock market in which subjects were required to search for the best sell prices for their stocks. By randomly assigning subjects into pairs and presenting them with real-time information on their peers' searches, we investigated the effects of peers' decisions on search behaviors. The results showed that two subjects in the same group with real-time peer information learned and engaged in similar search behaviors. However, this peer effect did not exist when subjects had access to feedback information on the ex-post best response. In addition, we found that the presence of information about peers' decisions alone had no significant impact on search efficiency, whereas access to both information on peers' decisions and feedback information significantly improved subjects' search efficiency.