Item Infomation
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Young-Woo, Lee | - |
dc.contributor.author | Heung-Seok, Chae | - |
dc.date.accessioned | 2023-04-25T08:13:06Z | - |
dc.date.available | 2023-04-25T08:13:06Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | https://link.springer.com/article/10.1007/s00521-023-08265-x | - |
dc.identifier.uri | https://dlib.phenikaa-uni.edu.vn/handle/PNK/8297 | - |
dc.description | CC BY | vi |
dc.description.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. | vi |
dc.language.iso | en | vi |
dc.publisher | Springer | vi |
dc.subject | CNNs | vi |
dc.title | Identification of untrained class data using neuron clusters | vi |
dc.type | Book | vi |
Appears in Collections | ||
OER - Công nghệ thông tin |
Files in This Item:
Restricted Access
Size : 1,82 MB
Format : Adobe PDF