四种机器学习算法在MNIST数据集上的对比研究

Comparative study of four machine learning algorithms on the MNIST dataset

MNIST数据集是检验机器学习算法性能常用的数据集。本文以MNIST数据集为例,研究四种机器学习方法的性能。首先,介绍支撑向量机、随机森林、BP神经网络和卷积神经网络;其次,将四种学习方法在MNIST数据集上训练学习;最后,对四种学习模型的性能做对比分析。就实验结果而言,卷积神经网络在性能上优于其它三种学习算法。

The MNIST dataset is a commonly used data set for testing the performance of machine learning algorithms.This paper uses the MNIST dataset as an example to study the performance of four machine learning methods.First,support vector machines,random forests,BP neural networks and convolutional neural networks are introduced.Then the four learning methods are trained and learned on the MNIST data set.Finally,the performance of the four learning models is compared and analyzed.As far as the experimental results are concerned,the performance of the convolutional neural network is better than the other three learning algorithms.