深度学习
2 Articles
-
【Deep Learning】Coursework Solution
| | Conv2d 实现
源码: 源码
Conv = unfold + maymul + fold
unfold函数理解
-
Deep Learning
| Curse of dimensionality
As the number of feature grows, the amount of data we need to generalise accurately grows exponentially.
- 覆盖特征值范围20%所需的训练样本数量随着维度增加呈指数型增长.
- 维度d很大时,超球面的体积趋于零.