Introduction to convolutional neural network using Keras; an understanding from a statistician
Introduction to convolutional neural network using Keras; an understanding from a statistician
复制标题
DOI：
10.29220/csam.2019.26.6.591
复制
发表时间：
2019-11-01
影响因子：
0.4
通讯作者：
Song, Jongwoo
中科院分区：
文献类型：
--
作者：
Lee, Hagyeong;Song, Jongwoo
深度学习是一种利用非线性变换从海量数据中发现特征的机器学习方法。它现在被广泛用于许多领域的监督学习。特别是，卷积神经网络(CNN)是自2012年以来最好的图像分类技术。对于考虑将深度学习模型用于现实世界应用程序的用户，KERAS是一个用Python语言编写的神经网络的流行API，也可以在R中使用。我们尝试从基础到高级技术研究深度神经网络的参数估计过程和CNN模型的结构。我们还试图找出CNN中的一些关键步骤，这些步骤可以使用KERAS来提高CIFAR10数据集中的图像分类性能。我们发现，几层卷积层和批归一化可以提高预测性能。我们还在MNIST和CIFAR10数据集中将图像分类性能与其他机器学习方法进行了比较，包括K-近邻(K-NN)、随机森林和XGBoost。
Deep Learning is one of the machine learning methods to find features from a huge data using non-linear transformation. It is now commonly used for supervised learning in many fields. In particular, Convolutional Neural Network (CNN) is the best technique for the image classification since 2012. For users who consider deep learning models for real-world applications, Keras is a popular API for neural networks written in Python and also can be used in R. We try examine the parameter estimation procedures of Deep Neural Network and structures of CNN models from basics to advanced techniques. We also try to figure out some crucial steps in CNN that can improve image classification performance in the CIFAR10 dataset using Keras. We found that several stacks of convolutional layers and batch normalization could improve prediction performance. We also compared image classification performances with other machine learning methods, including K-Nearest Neighbors (K-NN), Random Forest, and XGBoost, in both MNIST and CIFAR10 dataset.