Differences
This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
notes:deep-learning [2022/07/18] – gomida | notes:deep-learning [2022/11/20] (current) – gomida | ||
---|---|---|---|
Line 1: | Line 1: | ||
====== Deep Learning ====== | ====== Deep Learning ====== | ||
+ | |||
\\ | \\ | ||
- | \\ | ||
- | <sq> | ||
이안 굿펠로우, | 이안 굿펠로우, | ||
- | \\ | + | |
- | \\ | + | |
> The important principle is that careful specialization of numerical computation routines can yield a large payoff. Other strategies, besides choosing whether to use fixed or floating point, include optimizing data structures to avoid cache misses and using vector instructions. | > The important principle is that careful specialization of numerical computation routines can yield a large payoff. Other strategies, besides choosing whether to use fixed or floating point, include optimizing data structures to avoid cache misses and using vector instructions. | ||
\\ | \\ | ||
> Many machine learning researchers neglect these implementation details, but when the performance of an implementation restricts the size of the model, the accuracy of the model suffers. | > Many machine learning researchers neglect these implementation details, but when the performance of an implementation restricts the size of the model, the accuracy of the model suffers. | ||
- | </sq> | + | \\ |