tdc

London, United Kingdom

tomdiethe.com

Age: 35

Software Engineer, interests in Machine Learning and Computational Statistics

top accounts reputation activity favorites subscriptions

How do I find Wally with Python?

python image-processing machine-learning computer-vision asked Jan 13 '12 at 11:28

stackoverflow.com

25 votes

Why aren't Tour de France riders going any faster?

racing nutrition speed history technology asked Jan 13 '12 at 12:29

bicycles.stackexchange.com

16 votes

How does a Support Vector Machine (SVM) work?

machine-learning classification svm asked Feb 16 '12 at 13:25

stats.stackexchange.com

11 votes

What's the correct way to test the significance of classification results

classification statistical-significance asked Feb 8 '12 at 16:20

stats.stackexchange.com

10 votes

Opening strategies in Chess 960 (Fisher Random Chess)

chess openings variants asked Dec 20 '11 at 9:29

boardgames.stackexchange.com

9 votes

In boosting, why are the learners “weak”?

machine-learning theory boosting asked Feb 16 '12 at 13:37

stats.stackexchange.com

7 votes

Combining n-grams

text-mining asked Nov 24 '11 at 18:11

stats.stackexchange.com

6 votes

Close all open files in ipython

python ipython filehandle asked Jan 24 '12 at 16:27

stackoverflow.com

6 votes

Dealing with very large time-series datasets

machine-learning feature-selection large-data feature-construction asked Feb 17 '12 at 10:56

stats.stackexchange.com

6 votes

Beyond Fisher kernels

machine-learning kernel probability asked Feb 17 '12 at 10:02

stats.stackexchange.com

Top Answers

How would you design a machine learning system to play Angry Birds?

stats.stackexchange.com

Why do naive Bayesian classifiers perform so well?

stats.stackexchange.com

How to decide on the correct number of clusters?

stats.stackexchange.com

PCA, LDA, CCA, and PLS

stats.stackexchange.com

Does a sparse training set adversely affect an SVM?

stats.stackexchange.com

Probabilistic graphical models textbook

stats.stackexchange.com

Why do we assume that the error is normally distributed?

stats.stackexchange.com

What is the correct capitalisation of the word “sonar”?

english.stackexchange.com

Classification with tall fat data

stats.stackexchange.com

Fast method for finding best metaparameters of SVM (that is faster than grid search)

stats.stackexchange.com

Why “bother” with a null hypothesis at all?

math.stackexchange.com

What are the “hot algorithms” for machine learning?

stats.stackexchange.com

How can I help ensure testing data does not leak into training data?

stats.stackexchange.com

Is whitening always good?

stats.stackexchange.com

Are there algorithms for computing “running” linear or logistic regression parameters?

stats.stackexchange.com

What is the proper naming scheme for dataset parts?

stats.stackexchange.com

Why is there no Recycle Bin?

askubuntu.com

Is it a bad idea to take a commuter bike for a 50 - 100km ride?

bicycles.stackexchange.com

What are the differences between these two Gabor filter functions

dsp.stackexchange.com