Identification of untrained class data using neuron clusters

Abstract

Convolutional neural networks (CNNs), a representative type of deep neural networks, are used in various fields. There are problems that should be solved to operate CNN in the real-world. In real-world operating environments, the CNN’s performance may be degraded due to data of untrained types, which limits its operability. In this study, we propose a method for identifying data of a type that the model has not trained on based on the neuron cluster, a set of neurons activated based on the type of input data. In experiments performed on the ResNet model with the MNIST, CIFAR-10, and STL-10 datasets, the proposed method identifies data of untrained and trained types with an accuracy of 85% or higher. The more data used for neuron cluster identification, the higher the accuracy; conversely, the more complex the dataset's characteristics, the lower the accuracy. The proposed method uses only the information of activated neurons without any addition or modification of the model’s structure; hence, the computational cost is low without affecting the classification performance of the model.

Assessment of artificial intelligence to detect gasoline in fire debris using HS‐SPME‐GC/MS and transfer learning

“…Hence, the training time is shortened, and the computation efficiency is increased. The shortcomings of the CNNs are the prerequisite of a considerable amount of training data and the limited capability to generalize to new data that are different from the training data [17, 18]. Nevertheless, CNNs have been an active field in various image classification tasks, such as medical diagnosis [19, 20], natural and man‐made disaster management [21–23], environmental conservation [24, 25], food industry [26, 27], etc.…”