In order to avoid overfitting in deep convolutional neural networks, a new regularization method called deterministic DropConnect is proposed. The main idea of the deterministic DropConnect is to reduce the spatial dimension of the convolution filter by selectively discarding the partial connection, according to the contributions of the different weights of the convolutional filters to the result. The connections between the layers of the convolutional neural networks are more sparse. In this paper, the effectiveness of the proposed deterministic DropConnect is evaluated on the task of image classification. The error rates are 0.32%, 5.33% and 26.88% in the MNIST, CIFAR-10 and CIFAR-100 datasets, respectively. Compared with the original experimental error rates, the error rates reduce by 0.15%, 1.09% and 1.36%, respectively. Experiments show that the proposed algorithm is an effective method to deal with the overfitting in neural networks, and can improve the robustness and generalization ability of the convolutional neural networks.

deep learning; convolutional neural networks; regularization; DropConnect 深度学习（deep learning，DL）是近年来机器学习领域的一个研究热点。深度卷积神经网络（deep convolutional neural network）作为深度学习中一种极具代表性的网络结构，在计算机视觉、自动驾驶、广告推荐、自然语言处理和生命科学等领域均取得了突破性进展，有着广泛的应用前景。深度卷积神经网络通过构造深度学习模型，让模型自主地从海量训练数据中学习特征，用于提升对未来样本或未知事件的判断和预测能力。不同于传统的手工设计特征，通过大数据学习得到的特征更能刻画数据丰富的内在信息。这也是深度学习模型在大数据领域越来越受关注的本质原因。为了更好地将深度卷积神经网络应用于现实生活中，很多研究都致力于构建更好\[1-2\]和更快\[3-4\]的深度学习模型。