在这篇论文中，我们研究了关于深度学习的主题，重点是利用卷积神经网络进行图像识别。本文涵盖了深度学习的各个组成部分，包括网络结构、反向传播和随机梯度下降。我们将解释这些组件的基本原理，并将理论与实践进行比较。然后，我们研究卷积神经网络及其组成的各层结构。最后，我们建立并训练一个卷积神经网路来分类小型的彩色影像，该网络的识别准确率达到85%左右。 

In this thesis, we study the topic of deeplearning with a focus on image recognition using convolutional neural networks.We cover the various components of deep learning, including the networkstructure, backpropagation and stochastic gradient descent. We explain thefundamentals of these components and compare theory to practice. We thenexamine convolutional neural networks and the various layers they consist of.Finally, we build and train a convolutional neural network to classify smallimages of coloured shapes. This network achieved an accuracy of around 85%.

1.  引言

2. 深度学习的基本理论

3. 深度神经网络

4. 反向传播

5. 随机梯度下降

6. 图像识别中的卷积神经网络

https://089u.com/f/1850492-503498170-d67c92

（访问密码：3660）