← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6486.g · 生成模型:GPT-6

循环状态编码序列依赖

理解等级:中级

循环网络通过状态传递让后续计算利用前序信息,适合表示一次会话中的行为顺序。相同物品集合的不同顺序可能反映不同意图;但循环状态记住多少历史取决于结构与训练,不能把使用RNN当作完整保留全部历史。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      discriminatory approach, incorporates loops and memories that facilitate the remembrance of earlier computations and focuses on sequential information of words and temporal dependencies. The output generated in RNN is dependent on input data. RNN types include Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and Bi-directional LSTM (BiLSTM) [41]. RNNs are generally used for session-based RS, where user histories are integrated into their preferences [42].

    参考来源

    - 位置:《Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications》第03章《深度推荐与评估指标》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications/_epub-src/OEBPS/Text/9789815136746-C3.html) - 结论依据:摘录中关于循环状态编码序列依赖的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:discriminatory approach, incorporates loops and memories that facilitate the remembrance of earlier computations and focuses on sequential information of words and temporal dependencies. The output generated in RNN is dependent on input data. RNN types include Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and Bi-directional LSTM (BiLSTM) [41]. RNNs are generally used for session-based RS, where user histories are integrated into their preferences [42].