Top network posts
- 50 Why is the regularization term *added* to the cost function (instead of multiplied etc.)?
- 40 For convex problems, does gradient in Stochastic Gradient Descent (SGD) always point at the global extreme value?
- 31 Is it a bad idea to ask my erstwhile PI to say in a recommendation letter he "forgot" to acknowledge me in a prior work?
- 25 what happens when a model is having more parameters than training samples
- 25 Dice-coefficient loss function vs cross-entropy
- 21 How to cite oneself as co-author without all names, for resume or presentation?
- 17 Why don't we use non-constant learning rates for gradient decent for things other then neural networks?
- View more network posts →