Top network posts
- 47 Why is the regularization term *added* to the cost function (instead of multiplied etc.)?
- 33 For convex problems, does gradient in Stochastic Gradient Descent (SGD) always point at the global extreme value?
- 21 How to cite oneself as co-author without all names, for resume or presentation?
- 16 Why don't we use non-constant learning rates for gradient decent for things other then neural networks?
- 14 Second order approximation of the loss function (Deep learning book, 7.33)
- 12 Dice-coefficient loss function vs cross-entropy
- 12 Why isn't "Saddle-Free Newton" descent algorithm used in practice?
- View more network posts →
Top tags (9)
19 Links to copyright material Mar 19 '18