Transformer的简单实现:CS224n作业5代码解析 本文是CS224n作业5的项目解析。 数据 预训练数据集:wiki 该数据集为txt格式,每行的内容为:人名+关于这个人的一段介绍,每个人之间的描述文本由分行符分隔,选取前三行内容如下: Khatchig Mouradian. Khatchig Mouradian is a journalist, writer and translator born in...
Recurrent Neural Networks and Language Models (语言模型与循环神经网络) 课后作业:无 Vanishing Gradients and Fancy RNNs(梯度弥散与RNN进阶) 注:感谢@gongle提供中文字幕 课后作业:https://github.com/xixiaoyao/CS224n-winter-together/tree/master/Assignments/assignment4 也可订阅号「夕小瑶的卖萌屋」后台回复...