jpmuc's user avatar
jpmuc's user avatar
jpmuc's user avatar
jpmuc
  • Member for 10 years, 9 months
  • Last seen this week
  • Minga
118 votes
Accepted

tanh activation function vs sigmoid activation function

70 votes

Gradient Boosting Tree vs Random Forest

35 votes
Accepted

What is one class SVM and how does it work?

32 votes
Accepted

What does kernel size mean?

20 votes
Accepted

Is KNN a discriminative learning algorithm?

19 votes
Accepted

Where is density estimation useful?

16 votes

Machine learning algorithms to handle missing data

15 votes
Accepted

Why not always use ensemble learning?

15 votes
Accepted

Why is gradient descent required?

14 votes
Accepted

How to calculate optimal zero padding for convolutional neural networks?

14 votes
Accepted

Curse of dimensionality: kNN classifier

14 votes

Why is optimizing a mixture of Gaussian directly computationally hard?

14 votes

Softmax layer in a neural network

13 votes
Accepted

Having a conjugate prior: Deep property or mathematical accident?

13 votes

Does k-NN with k=1 always implies overfitting?

12 votes

What are good initial weights in a neural network?

11 votes
Accepted

Why must one trade off between bias and variance?

10 votes
Accepted

Mathematical background for neural networks

10 votes

Machine Learning to Predict Class Probabilities

10 votes
Accepted

Iterative process for removing extreme samples

10 votes
Accepted

Non-orthogonal technique analogous to PCA

10 votes

Regression vs. classification and generative vs. discriminative

10 votes

Choosing filter size, strides etc. in a CNN?

9 votes

What machine learning techniques can, once trained, generate prediction despite some missing inputs?

8 votes
Accepted

Visualizing high dimensional data

8 votes

LibSVM cost weights for unbalanced data doesn't work

8 votes

In Naive Bayes, why bother with Laplace smoothing when we have unknown words in the test set?

8 votes
Accepted

Differences between Multi-layer NN, Hopfield, Helmholtz and Boltzmann machines

8 votes
Accepted

stick breaking model of Dirichlet process

7 votes

Is linear discriminant analysis (LDA) more likely to overfit than support vector machine (SVM)?

1
2 3 4 5
9