知识卡片
损失地形取决于模型和损失
线性预测配平方损失或逻辑模型配适当交叉熵可有凸目标,多层非线性网络通常更复杂。局部极小、鞍点、平坦区和数值问题都可能影响训练;看见损失下降并不等于已找到全局最优或泛化最好的参数。
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
- · 神经网络基础
原书出处 · 1 处
- · 查看原书依据
What does this visualization represent? At each epoch, the algorithm is performing gradient descent in trying to minimize the error. Each time you adjust the weights in a direction, you will hopefully reduce your error the next time. A convex error surface will be great. Stand on the ski slope, look around, find out which way is down, and go that way!
参考来源
- 位置:《Natural Language Processing in Action, Second Edition》第05章《神经网络基础》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-5.html)
- 结论依据:摘录中关于损失地形取决于模型和损失的定义、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:What does this visualization represent? At each epoch, the algorithm is performing gradient descent in trying to minimize the error. Each time you adjust the weights in a direction, you will hopefully reduce your error the next time. A convex error surface will be great. Stand on the ski slope, look around, find out which way is down, and go that way!