Data Science
Network profile
645
reputation
4
12

user781486

Apparently, this user prefers to keep an air of mystery about them.

0
answers
18
questions
~21k
people reached
  • Member for 1 year, 6 months
  • 10 profile views
  • Last seen Jan 20 at 13:16

Communities (56)

Top network posts

Top tags (28)

Score 0
Posts 15
Posts % 83
Score 0
Posts 5
Score 0
Posts 4
Score 0
Posts 3
Score 0
Posts 3
Score 0
Posts 3
View all tags →

Top posts (18) All Questions Answers | Votes Newest

13 Why does adding a dropout layer improve deep/machine learning performance, given that dropout suppresses some neurons from the model? Aug 16 '18
9 When should one use L1, L2 regularization instead of dropout layer, given that both serve same purpose of reducing overfitting? Aug 23 '18
7 What are some situations when normalizing input data to zero mean, unit variance is not appropriate or not beneficial? Sep 3 '18
6 Why does the naive bayes algorithm make the naive assumption that features are independent to each other? Sep 2 '18
4 How to handle “unknown” category in machine learning classification problems? Sep 2 '18
3 What does high variance mean in a binary classification machine learning model? Aug 28 '19
2 Why is the softmax function often used as activation function of output layer in classification neural networks? Aug 23 '18
2 Is it a good practice to always apply `ReduceLROnPlateau()`, given that models benefit from reducing learning rate once learning stagnates? Aug 20 '18
2 Is the multilayer perceptron only able to accept 1d vector of input data? If yes, why is this so? Aug 18 '18
1 Why is there a trade-off between bias and variance in supervised learning? Why can't we have best of both worlds? Aug 27 '19
View all questions and answers →

Badges (16)

Gold

—

Silver

4

Rarest

Bronze

12

Rarest

View all badges →