Samo Jerom's user avatar
Samo Jerom's user avatar
Samo Jerom's user avatar
Samo Jerom
  • Member for 11 years, 4 months
  • Last seen more than 2 years ago
38 votes
4 answers
101k views

Area under curve of ROC vs. overall accuracy

15 votes
3 answers
20k views

Does Neural Networks based classification need a dimension reduction?

11 votes
3 answers
8k views

Does ICA require to run PCA first?

11 votes
3 answers
4k views

PCA, ICA and Laplacian eigenmaps

10 votes
1 answer
10k views

Should PCA be performed before I do classification?

10 votes
1 answer
3k views

A valid distance metric for high dimensional data

7 votes
2 answers
3k views

Confused about sensitivity, specificity and area under ROC curve (AUC)

7 votes
3 answers
4k views

How to get a valid distance metric?

6 votes
1 answer
833 views

Quantitative results of cluster analysis

5 votes
3 answers
662 views

How 'deep' is deep for auto-encoders based deep learning?

4 votes
3 answers
5k views

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

4 votes
1 answer
9k views

How to define the maximum k of the kNN classifier?

4 votes
1 answer
2k views

What exactly the ROC curve can tell us or can be inferred?

3 votes
1 answer
3k views

What are the differences of the Student's T-Test, KS-Test and the MWW-Test?

3 votes
2 answers
2k views

Novelty and Outlier Detection for Multi-label Data

3 votes
0 answers
169 views

Centering for the regression. How to do it properly?

2 votes
2 answers
717 views

Semi-supervised Learning Training

2 votes
0 answers
483 views

Semi-supervised learning vs supervised learning, what are the benefits and limitations?

2 votes
1 answer
595 views

How to measure the similarity of k-means clustering using different datasets?

2 votes
3 answers
599 views

Shape analysis of an object to create features for pattern recognition

2 votes
0 answers
2k views

How to compare the results of two classifiers are statistically significant different?

2 votes
1 answer
4k views

How to interpret the number of k in k-nearest-neighbour classifier?

1 vote
0 answers
1k views

Feature selection methods comparison

1 vote
1 answer
282 views

Better machine learning methods for medical imaging segmentation

1 vote
1 answer
1k views

Scatter plot or 2D histogram for mixture of Gaussian fitting?

1 vote
2 answers
2k views

How to combine the information of two probabilities?

1 vote
1 answer
1k views

Question of unary term (data term) of the graph cut method

1 vote
2 answers
703 views

How many features can we use to avoid overfitting the classification?

1 vote
0 answers
821 views

Parameters tuning for auto-encoders

1 vote
1 answer
2k views

Is there a minimum image size for successful deep auto-encoders?