1. 毕业设计（论文）的内容和要求

深度学习是近十年来人工智能领域使用最为广泛的技之一。

它在语音识别、自然语言处理、计算机视觉、图像与视频分析等诸多领域都取得了令人满意的成果。

特别在图像识别领域取得了巨大的成就，具有非常重要的研究意义。

2. 参考文献

[1] Hopfield JJ. Neural networks and physical systems with emergent collective computational abilities. Proc. of the National Academy of Sciences of the United States of America, 1982, 79(8): 2554#8211;2558. [2] Rumelhart D, Hinton GE, William R. Learning representations by back-propagating errors. Nature, 1986, 323(6088): 533#8211;536. [3] Hinton GE, Salakhutdinov R. Reducing the dimensionality of data with neural networks. Science, 2006, 313(7): 504#8211;507. [4] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, eds. Proc. of the Advances in Neural Information Processing Systems. Lake Tahoe: Neural Information Processing Systems Foundation. 2012. 1106#8211;1114. [5]Deng J, Berg A, Satheesh S. Large scale visual recognition challenge. http://www.image-net.org/challenges/LSVRC/2012/ index, 2013. [6] Perronnin F, Snchez J, Mensink T. Improving the fisher kernel for large-scale image classification. Proc. of the European Conference on Computer Vision. Crete: Springer Berlin Heidelberg. 2010. 6314. 143#8211;156. [7]余凯,贾磊,陈雨强,徐伟.深度学习的昨天、今天和明天.计算 机研究与发展,2013,50(9):1799#8211;1804. [8] 郑胤,陈权崎,章毓晋.深度学习及其在目标和行为识别中的新进展.中国图象图形学报,2014,19(2):175#8211;184. [9] Jose CA. Fast On-line alogrithm for PCA and its convergence characteristic. IEEE Trans. on Neural Network, 2000,4(2):299-307. [10] Tenenbaum JB, de Silva V, Langford JC. A global geometric framework for nonlinear dimensionality reduction. Science, 2000, 290(5500): 2319#8211;2323. [11] Roweis ST, Saul LK. Nonlinear dimensionality reduction by locally linear embedding. Science, 2000, 290(5500): 2323#8211; 2326. [12] Belkin M, Niyogi P. Laplacian eigenmaps for dimensionality reduction and data representation. Neural Vomputation, 2002, 15: 1373#8211;1396. [13] Donoho DL, Grimes C. Hessian eigenmaps: Locally linear embedding techniques for high dimensional data. PNAS, 2003, 100(10): 5591#8211;5596. [14] Zhang Z, Zha HY. Principal manifolds and nonlinear dimensionality reduction via tangent space alignment. SIAM Journal on Scientific Computing, 2004, 26(1): 313#8211; 338. [15] Andrew N. UFLDL_Tutorial. http://deeplearning.stanford. edu/wiki/index.php/UFLDL_Tutorial, 2015. [16] Vincent P, Larochelle H, Bengio Y. Extracting and composing robust features with denoising autoencoders. Proc. of the 25th International Conference on Machine Learning. New York: ACM. 2008. 1096#8211;1103. [17] 刘建伟,刘媛,罗雄麟.玻尔兹曼机研究进展.计算机研究与 发展,2014,51(1):1#8211;16. [18] Liu JS. Monte Carlo strategies in scientific computing. 1th ed., New York: Springer-Verlag, 2001: 129#8211;151. [19] Hinton GE. Training products of experts by minimizing contrastive divergence. Neural Computation, 2002, 14(8): 1771#8211;1800. [20] Cho K, Raiko T, Ilin A. Parallel tempering is efficient for learning restricted Boltzmann machines. Proc. of 2010 International Joint Conferrence on Neural Networks. New York. ACM. 2010. 1#8211;8. [21] Desjardins G, Courville A, Bengio Y. Tempered Markov chain Monte Carlo for training of restricted Boltzmann machines. Journal of Machine Learning Research- Processing Track, 2010, 9(1): 145#8211;152. [22] Cho K, Raiko T, Ilin A. Enhanced gradient and adaptive learning rate for training restricted Boltzmann machines. Proc. of 28th International Conferrence on Machine Learning. New York. ACM. 2011. 105#8211;112. [23] Bengio Y. Learning deep architectures for AI. Foundations and Trends in Machine Learning, 2009, 2(1): 1#8211;127. [24] Hinton GE, Osindero S, Teh YW. A fast learning algorithm for deep belief nets. Neural Computation, 2006, 18(7): 1527#8211;1554. [25] 刘建伟,刘媛,罗雄麟.深度学习研究进展.计算机应用与研 究,2014,31(7):1921#8211;1942. [26] 尹宝才,王文通,王立春.深度学习研究综述.北京工业大学 学报,2015,41(1):48#8211;59. [27] 王蕾,张宝昌.深度学习新研究进展综述.中国科技论文 在线,2015,8(6):510#8211;517.

3. 毕业设计（论文）进程安排

起讫日期 设计（论文）各阶段工作内容 备 注 2018.1.8-1.10 确定题目 2018.1.11-1.31 查阅参考文献，了解课题要求，完成开题报告 完成英文翻译 2018.3.1-3.15 完成系统相关理论分析 深度学习无监督相关理论 2018.3.16-3.25 完成系统相关模型分析 深度学习无监督相关模型 2018.3.26-4.15 初步完成整个系统的模型编写实现 2018.4.16-5.1 系统优化及图像数据测试 2018.5.2-5.5 撰写测试软件使用说明书 MATLAB等相关工具 2018.5.6-5.21 撰写论文，并通过电子邮件发给指导老师审核 2018.5.22-5.27 按指导老师意见修改论文并定稿打印装订 2018.5.28-6.15 准备毕业论文的答辩,包括答辩演示文稿等