| [21.05.27] 박사학위논문발표 | |||||
| 작성자 | 이** | 작성일 | 2021-05-25 | 조회수 | 271 |
|---|---|---|---|---|---|
|
박사학위논문발표 1. 발표자 : 알모마니 레잇 모하마드 이사 2. 소속 : 울산대학교 일반대학원 수학과 3. 발표일시 : 5월 27일 오후 2시 ~ 3시30분 4. 장소 : 8- 426 호 5. 제목 : Extension and optimization of the perceptron convergence algorithm. (퍼셉트론 수렴 알고리즘의 확장과 최적화) 6. 초록 : Artificial neural networks has been used in diverse area and played an important role. However there are a few mathematical analysis of neural networks. Especially, as far as we know, there is no theoretical approach to constructthe order of training data for accelerating the convergence speed of neural network algorithms. For the construction, we consider the single layer perceptron convergence algorithmand make new convergence algorithms for different structures of the perceptron as well as their convergence proofs. We present the order of training data for higher speed acceleration performance based on the convergenceproof. Finally, we provide numerical examples of extended convergence theorems and the order of training data. |
|||||