论文标题
用于MNIST数字识别的简单卷积神经网络模型的合奏
An Ensemble of Simple Convolutional Neural Network Models for MNIST Digit Recognition
论文作者
论文摘要
我们报告说，通过使用简单的卷积神经网络（CNN）模型可以实现MNIST测试集的高度精度。我们在卷积层中使用三种不同的模型，其中包括3x3、5x5和7x7内核大小。每个模型都由一组卷积层组成，然后是单个完全连接的层。每个卷积层都使用批归归式化和恢复激活，并且不使用合并。旋转和翻译用于增强培训数据，该数据经常用于大多数图像分类任务。使用在训练数据集上独立培训的三种模型进行的多数投票，可以在测试集上获得高达99.87％的精度，这是最先进的结果之一。两层合奏是三个均匀合奏网络的异质集合，最高可达到99.91％的测试准确性。可以通过使用：https：//github.com/ansh941/mnistsimplecnn来复制结果
We report that a very high accuracy on the MNIST test set can be achieved by using simple convolutional neural network (CNN) models. We use three different models with 3x3, 5x5, and 7x7 kernel size in the convolution layers. Each model consists of a set of convolution layers followed by a single fully connected layer. Every convolution layer uses batch normalization and ReLU activation, and pooling is not used. Rotation and translation is used to augment training data, which is frequently used in most image classification tasks. A majority voting using the three models independently trained on the training data set can achieve up to 99.87% accuracy on the test set, which is one of the state-of-the-art results. A two-layer ensemble, a heterogeneous ensemble of three homogeneous ensemble networks, can achieve up to 99.91% test accuracy. The results can be reproduced by using the code at: https://github.com/ansh941/MnistSimpleCNN
