研究資料首頁-> 期刊論文
研究資料明細
| 論文名稱 | Deep Multi-Layer Neural Network with Variable-Depth Output |
| 發表日期 | 2023-12-01 |
| 論文收錄分類 | SCI |
| 所有作者 | 楊雄斌,梁丁文 |
| 作者順序 | 第一作者 |
| 通訊作者 | 是 |
| 刊物名稱 | International Journal of Pattern Recognition and Artificial Intelligence |
| 發表卷數 | 37 |
| 是否具有審稿制度 | 是 |
| 發表期數 | 15 |
| 期刊或學報出版地國別/地區 | NATGBR-英國 |
| 發表年份 | 2024 |
| 發表月份 | 12 |
| 發表形式 | 紙本及電子期刊 |
| 所屬計劃案 | 無 |
| 可公開文檔 |
|
| 可公開文檔 |
|
| 可公開文檔 |
|
| 附件 |
 2023 Deep MultiLayer Neural Network with VariableDepth Output.pdf
|
[英文摘要] :
In this study, a deep multi-layer neural network (DMLNN) with variable-depth out
put (VDO), called VDO-DMLNN, is proposed for classification. Unlike the traditional
DMLNN, for which a user must define the network architecture in advance, VDO
DMLNN is produced from the top–down, layer by layer, until the classification error
rate of VDO-DMLNN no longer decreases. The user thus does not need to define the
depth of VDO-DMLNN in advance. The combination of the genetic algorithm (GA) and
the self-organizing feature map (SOFM), called GA–SOFM, is proposed to automati
cally generate the weights and proper number of nodes for each layer in VDO-DMLNN.
In addition, the output nodes can be at different levels in VDO-DMLNN rather than all
being at the last layer, as in the traditional DMLNN. Thus, the average of computing
time required for the recognition of an input sample in VDO-DMLNN is less than that
in traditional DMLNN when they have the same classification error rate. Finally, VDO
DMLNN is compared with some state-of-the-art neural networks in the experiments.
[參考文獻] :
In this study, a deep multi-layer neural network (DMLNN) with variable-depth out
put (VDO), called VDO-DMLNN, is proposed for classification. Unlike the traditional
DMLNN, for which a user must define the network architecture in advance, VDO
DMLNN is produced from the top–down, layer by layer, until the classification error
rate of VDO-DMLNN no longer decreases. The user thus does not need to define the
depth of VDO-DMLNN in advance. The combination of the genetic algorithm (GA) and
the self-organizing feature map (SOFM), called GA–SOFM, is proposed to automati
cally generate the weights and proper number of nodes for each layer in VDO-DMLNN.
In addition, the output nodes can be at different levels in VDO-DMLNN rather than all
being at the last layer, as in the traditional DMLNN. Thus, the average of computing
time required for the recognition of an input sample in VDO-DMLNN is less than that
in traditional DMLNN when they have the same classification error rate. Finally, VDO
DMLNN is compared with some state-of-the-art neural networks in the experiments.
