A Fast Algorithm for Recurrent Neural Networks
-
摘要: 針對目前局部回歸神經網絡動態BP算法的誤差導數計算復雜、收斂速度慢的缺陷,提出了一種新的快速算法.該算法是將信號流圖引入動態BP算法,較好地解決了求解誤差導數的復雜性,同時采用BFGS算法加快了網絡的收斂速度.仿真結果表明了本算法的有效性.Abstract: A new fast learning algorithm for recurrent neural networks is proposed. By introducing the signal flow graphs technique, it overcomes the disadvantage of complexity of the gradient of the error function. And for more fast convergence, the BFGS method is used. Simulation results show that the proposed algorithm converges faster than the traditional algorithm.
-
Key words:
- recurrent neural networks /
- dynamic BP algorithm /
- signal flow graphs /
- BFGS
-
點擊查看大圖
計量
- 文章訪問數: 227
- HTML全文瀏覽量: 99
- PDF下載量: 7
- 被引次數: 0
下載:
