BP網(wǎng)絡(luò)不平衡訓(xùn)練樣本集的有效學(xué)習(xí)算法
AN EFFICIENT LEARNING ALGORITHM OF NONBALANCED TRAINING SET FOR BP NETWORK
-
摘要: 分析了BP網(wǎng)絡(luò)標(biāo)準(zhǔn)反傳學(xué)習(xí)算法對(duì)不平衡樣本集訓(xùn)練速度慢的原因,研究了如何改進(jìn)其學(xué)習(xí)算法來(lái)加速訓(xùn)練速度,并通過(guò)實(shí)驗(yàn)對(duì)上述理論進(jìn)行驗(yàn)證。
-
關(guān)鍵詞:
- 神經(jīng)網(wǎng)絡(luò); 不平衡訓(xùn)練集
Abstract: This paper analyzes the reason for low convergence rate of BP network standard backpropagation algorithm to nonblanced training set, researches how to improve the learning algorithm in order to increase training speed, and through two experiments tests and verifies above theory. -
Anand R,et al. Efficient classification for multiclass problem using modular neural networks. IEEE Trans. on Neural Networks, 1995, NN-6(1): 117-124.[2]Anand R, et al. An improved algorithm for neural networks classification of imbalanced training sets. IEEE Trans. on Neural Networks, 1993, NN-4(6): 962-969.[3]Waibel A, et al. Modularity and scaling in large phonemic neural networks. IEEE Trans. on ASSP, 1989, ASSP-37(12): 1888-1898.[4]Waibel A, et al. Phoneme recognition using time-delay neural networks. IEEE Trans. on ASSP, 1989, ASSP-37(3): 328-339. -
計(jì)量
- 文章訪問(wèn)數(shù): 2208
- HTML全文瀏覽量: 112
- PDF下載量: 405
- 被引次數(shù): 0
下載:
