声明
Introduction
1 Methods of deep learning
1.1 Unsupervised learning systems
1.2 Teaching with the teacher
2 Research purpose
2.1 MNIST Dataset
2.2 Software tools for solving problems of deep learning
3 Setting up libraries
3.1 Setup Caffe library
3.2 Setup Pylearn2 library
3.2 Setup Torch library
3.5 Test infrastructure
3.6 Network topologies and learning parameters
4 Experimental results
4.1 Library Evaluation Criteria
4.2 Scoring and comparing libraries
5 Conclusions and Future Work
5.1 Conclusions
5.2 Future Work
致谢
参考文献
Academic Achievements
兰州交通大学;
