Sequential three-way decisions with a single hidden layer feedforward neural network

They have been widely implemented in applications, including video frame inpainting [33] and automatic driving [31]. The performance of neural networks is mainly affected by hyperparameter selection and network topology. Hyperparameter selection [3, 4] is a classical topic in machine learning, which can be realized by grid search [26, 32] and particle swarm optimization [1, 24]. In addition, network topology [2, 30, 42] is the key of neural network design, which can be realized through three-way decisions [7] and an incremental learning mechanism [10, 15, 40]. To achieve an effective network structure, three-way decisions with a single hidden layer feedforward neural network (TWD-SFNN) [7] adopts a novel model to guide the number of hidden layer nodes. In addition, as a shallow neural network model, TWD-SFNN provides a new perspective for the topology design of multilayer neural networks, hence laying the theoretical foundation for the framework of deep learning. However, for practical applications, TWD-SFNN has two drawbacks: (i) in terms of the performance of TWD-SFNN, the generalization ability of TWD-SFNN needs to be further improved; and (ii) to analyze the relationship between the costs and number of hidden layer nodes more thoroughly, the process costs of TWD-SFNN need to be considered. To improve the generalization ability of neural networks on structured datasets, and further enrich the theoretical framework of deep learning, we employ sequential three-way decisions to guide the growth of the network topology.