Search

Aiming at the problems of low recognition accuracy and large calculation amount of age estimation, this paper proposes a staged single aggregation backbone network VoVNetv4. In order to improve the feature extraction ability of the network, the Regional One-Shot Aggregation (ROSA) module is proposed in the network for regional encapsulation of the feature module. The classifier adopts the COnsistent RAnk Logits (CORAL) framework, which can solve the problem of inconsistency of classifiers in ordered regression CNNs for multiple binary classification tasks. This paper conducts experimental verification on the Asian Face Age Dataset (AFAD) and compares it with other research methods. The experimental results show that VoVNetv4 can effectively improve the feature extraction and detection ability of the network and improve the detection efficiency of age estimation. [ABSTRACT FROM AUTHOR]

Machine learning (ML) is evolving rapidly and has made many theoretical breakthroughs while widely applied in various fields. ML allows systems the ability to access data and use it to enable computers to execute cognitive processes such as learning and improving from previous experiences and solving complicated issues. Many first-order stochastic optimization methods have been used to solve the optimization model of ML. These algorithms adopt Barzilai-Borwein (BB) step size instead of fixed or diminishing step size to improve performance. However, the BB step size format involves fractional calculation, which inevitably leads to a zero denominator, especially when the objective function is non-convex. The BB technique will be violated if the denominator is near 0 or even negative. To improve the computation of the step size, a Positive Defined Stabilized Barzilai-Borwein (PDSBB) approach is introduced in this paper. Integrating PDSBB with the stochastic variance reduced gradient (SVRG) approach, a new method SVRG-PDSBB is proposed. Numerical experiments have shown that the new algorithm has stabilized the performance of the new step size, which successfully avoiding zero denominators and effectively solving the common problems in machine learning. The convergence of SVRG-PDSBB is theoretically and numerically proven, and the effectiveness of the new algorithm is shown by comparison with other algorithms. [ABSTRACT FROM AUTHOR]

The main purpose of this paper is to determine a non-trivial tractable class of the maximum (k,m)-subsets problem. More specifically, we show that we can solve this problem in polynomial time for m = 1. Depending on the value of k with respect to n, we prove that in the best-case scenario our algorithm runs in O(√n) time. On the other hand, an upper bound for solving it is given by O(n4/k³). Furthermore, for the case where n = k², we design and implement an algorithm in Python that yields a solution in O(n5/2). [ABSTRACT FROM AUTHOR]

This paper deals with multi-objective school bus routing problem, which includes route balance, total number of school buses and total travel distance optimization objectives. An improved non-dominated sorting genetic algorithm (NSGAII) is proposed to solve this problem. First, the definition of measurement indicator that denotes the degree of route balance is given based on the analysis of the solved problem. And then, the multi-objective optimization function is provided. In the proposed algorithm, the individuals are obtained by using the tournament selection, sequential crossover and inverse mutation. The 2-opt neighborhood operator is adopted to improve the best individuals obtained in each iteration. At the same time, the route selection rule based on the degree of route balance is applied to select the final optimal solution set. The solution with better balance degree will be taken as the best solution. Finally, some benchmark instances are used to test the effectiveness of proposed algorithm. The results reveal that the proposed algorithm outperforms the standard NSGAII and Multi-objective Evolutionary Algorithm(MOEA). The experimental results also show that our algorithm has good stability. [ABSTRACT FROM AUTHOR]

The simulated annealing algorithm is a stochastic optimization method for solving optimization problems associated with a large search space. The efficiency of the algorithm depends on the adaptation of the cooling model. Despite this, the main disadvantage of this algorithm is that it does not take into account the state of the system while searching. Thus, it is difficult to predict the system convergence with the simulated annealing algorithm. However, neural networks in particular continuous Hopfield networks have proven their ability in the field of machine learning to make a decision. In this paper, we introduce continuous Hopfield networks to improve the convergence of the simulated annealing algorithm. The experimental results show that the hybrid approach produces a large number of stable sets. [ABSTRACT FROM AUTHOR]