Convolutional neural networks can express models very well, but this ability gives us overfitting problem. To avoid overfitting problem, dropout technique are proposed. However, it is sometimes not enough because convolutional neural networks include a huge number of weights and biases. In this paper, we propose a combination of dropout technique and parallel convolution. In our method, neural network has two parallel convolution layer, and average value of these two convolution layer is used as the input to the pooling layer. Our proposed neural network could improve generalization ability about 4% for the unknown test patterns.
雑誌名
宮崎大學工學部紀要
巻
46
ページ
309 - 312
発行年
2017-07-31
出版者
宮崎大学工学部
Miyazaki University
Faculty of Engineering, University of Miyazaki
リポジトリのご案内
平行平均畳み込み処理とドロップアウトによる畳み込みニューラルネットワークの汎化能力向上
本文
(1.11MB)
