| dc.contributor | 資管系 | - |
| dc.creator (作者) | 蔡瑞煌;林怡伶;楊仁瀚;商肯豪;曹莉玲 | - |
| dc.date (日期) | 2024-08 | - |
| dc.date.accessioned | 21-Aug-2026 10:44:37 (UTC+8) | - |
| dc.date.available | 21-Aug-2026 10:44:37 (UTC+8) | - |
| dc.date.issued (上傳時間) | 21-Aug-2026 10:44:37 (UTC+8) | - |
| dc.identifier.uri (URI) | https://ah.lib.nccu.edu.tw/item?item_id=184561 | - |
| dc.description.abstract (摘要) | 本發明揭露一種基於單隱藏層神經網路的適應性學習演算法，包含以下步驟：藉由初始化模組以前 m+1筆資料建立初始單層類神經網路。藉由篩選模組選擇當回合要訓練的資料，判斷當回合的單層類神經網路能否達到學習目標，若是，藉由重組模組遍歷所有隱藏節點，並進行刪除隱藏節點動作避免過擬合問題，若否，則藉由調校模組調整權重參數，判斷調整後的神經網路是否可被接受，若否，則藉由強記模組增加三個新的隱藏節點以取得可接受的神經網路，並由重組模組檢視隱藏節點來避免過擬合現象，接著新增資料並持續訓練直到所有訓練資料皆訓練完畢。 | - |
| dc.description.abstract (摘要) | An adaptive learning algorithm based on a single hidden layer neural network is disclosed. The algorithm includes the following steps: generating the initial single layer neural network with the first m+1 data by the initializing module; selecting the training data for the current round and determining whether the single layer neural network of the current round can achieve the learning goal. If so, checking all the hidden nodes by the reorganizing module and performing the deleting action to the hidden nodes to avoid the overfitting problems. If not, adjusting the weight parameters by the matching module and determining whether the adjusted neural network is acceptable. If not, adding three new hidden nodes by the cramming module to obtain the acceptable neural network. The hidden nodes of the updated network are checked by the reorganization module to avoid the overfitting. The training process continues adding new data until all the training data is trained. | - |
| dc.format.extent | 1781504 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.relation (關聯) | 申請案號：111129726
申請日期：2022/08/08
公開日期：2024/02/16
證書號數：I853288
發明人：蔡瑞煌、林怡伶、楊仁瀚、商肯豪、曹莉玲 | - |
| dc.title (題名) | 適應性學習演算法 | - |
| dc.title (題名) | Adaptive learning algorithm | - |
| dc.type (資料類型) | patent | - |
