The Eighty Five Percent Rule for optimal learning
oleh: Robert C. Wilson, Amitai Shenhav, Mark Straccia, Jonathan D. Cohen
| Format: | Article |
|---|---|
| Diterbitkan: | Nature Portfolio 2019-11-01 |
Deskripsi
Is there an optimum difficulty level for training? In this paper, the authors show that for the widely-used class of stochastic gradient-descent based learning algorithms, learning is fastest when the accuracy during training is 85%.