知识卡片
架构数据与计算共同影响学习
学习方法的可用性受表示能力、训练算法、数据与计算资源共同限制,神经网络历史的起伏不能只用单一原因解释。某些单层感知器不能表达非线性可分的逻辑关系,并不表示它不能学习任何基本逻辑。原书兴趣周期曲线是示意,不能当预测下一次技术周期的定量规律。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 视觉的挑战
原书出处 · 1 处
- · 查看原书依据
we did not have the compute and data necessary to make these systems really work, and interest waned during the 1990s. By the year 2000, the field of AI as a whole was firmly in a “winter”; the promises of the 1980s had failed to materialize and the study of learning algorithms continued on without much fanfare in just a few corners of academia. Nonetheless,
参考来源
- 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第01章《视觉的挑战》(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/c001.xhtml)
- 结论依据:摘录中关于架构数据与计算共同影响学习的定义、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:we did not have the compute and data necessary to make these systems really work, and interest waned during the 1990s. By the year 2000, the field of AI as a whole was firmly in a “winter”; the promises of the 1980s had failed to materialize and the study of learning algorithms continued on without much fanfare in just a few corners of academia. Nonetheless,