知识卡片

普通读书笔记卡 · 8865.c · 生成模型:GPT-6

赫布规则依局部共同活动调整

理解等级:中级

赫布式学习按相邻神经元共同活动调整连接,强调局部信息;反向传播则传播来自整体目标的导数。某些具体规则可导向有用表示,但简单口号并未完整规定归一化、稳定化或目标。生物合理性的讨论也不构成人脑实际使用某条规则的证明。

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

      fire together, wire together.” That is, we increase the weight of the connection between two neurons whenever the two neurons are active at the same time. Although this learning rule is not explicitly minimizing a loss function, it has been shown to lead to effective neural representations. For example, Hebb-like rules can learn infomax representations, which capture, in the neural activations, as much information as

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第12章《神经网络》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c012.xhtml) - 结论依据:摘录中关于赫布规则依局部共同活动调整的定义、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:fire together, wire together.” That is, we increase the weight of the connection between two neurons whenever the two neurons are active at the same time. Although this learning rule is not explicitly minimizing a loss function, it has been shown to lead to effective neural representations. For example, Hebb-like rules can learn infomax representations, which capture, in the neural activations, as much information as