One hot representation 降维

1. 稀疏矩阵(sparse matrix)

2. feature selection or feature filtering

参考文献:
A. Caliskan-Islam, R. Harang, A. Liu, A. Narayanan, C. Voss, F. Yamaguchi, and R. Greenstadt. 2015. De-anonymizing Programmers via Code Stylometry. In 24th USENIX Security Symposium (USENIX Security 15). USENIX Association, Washington, D.C., 255–270. https://www.usenix.org/conference/usenixsecurity15/
technical-sessions/presentation/caliskan-islam

X. Meng. 2016. Fine-grained Binary Code Authorship Identification. In Proceedings of the 2016 24th ACM SIGSOFT International Symposium on Foundations of Software Engineering (Seattle, WA, USA) (FSE 2016). ACM, New York, NY, USA, 1097–1099. https://doi.org/10.1145/2950290.2983962

N. Rosenblum, X. Zhu, and B. P. Miller. 2011. Who Wrote This Code? Identifying the Authors of Program Binaries. In Proceedings of the 16th European Conference on Research in Computer Security (Leuven, Belgium) (ESORICS’11). Springer-Verlag, Berlin, Heidelberg, 172–189. http://dl.acm.org/citation.cfm?id=2041225.2041239

word2vec的度一般情况下要远远小于词语总数的大小。它的度与隐含层节点数一致,是一种操作,将词语从one-hot encoder形式的表示到Word2vec形式的表示。\[1\]最终词向量的度可以根据具体的应用需求进行设置,但一般来说,常见的word2vec度为几十到几百。\[2\]这样的度可以在保留词语语义信息的同时,减少了计算和存储的开销。如果你对word2vec感兴趣,可以参考一些相关的学习资料,如《Word2Vec Tutorial—The Skip-Gram Model》、《Word Embedding Explained and Visualized》和《Vector Representation of Words》等。\[3\] #### 引用[.reference_title] - *1* *2* [如何通俗理解Word2Vec (23年修订版)](https://blog.youkuaiyun.com/v_JULY_v/article/details/102708459)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v91^koosearch_v1,239^v3^insert_chatgpt"}} ] [.reference_item] - *3* [大白话讲解word2vec到底在做些什么](https://blog.youkuaiyun.com/mylove0414/article/details/61616617)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v91^koosearch_v1,239^v3^insert_chatgpt"}} ] [.reference_item] [ .reference_list ]
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值