Reputation
8,036
Top tag
Next privilege 10,000 Rep.
Access moderator tools
Badges
1 20 97
Newest
 Yearling
Impact
~113k people reached

Feb
2
revised What are the time and space complexities of Classify/Predict?
added 529 characters in body
Feb
2
comment What are the time and space complexities of Classify/Predict?
Good idea, will try tonight... Ive always found complexity hard to get a handle on in mma because there's a lot going on under the hood. I thought maybe a dev would know offhand which libraries mma uses for each type of classifier
Feb
1
answered Is it possible to visually edit a graph?
Feb
1
asked What are the time and space complexities of Classify/Predict?
Jan
31
revised How to import/export to libsvm?
added 93 characters in body
Jan
29
asked How to import/export to libsvm?
Jan
29
awarded  Nice Question
Jan
28
accepted Detecting components in timeseries
Jan
27
revised Detecting components in timeseries
edited body
Jan
27
revised Detecting components in timeseries
edited body
Jan
27
revised Detecting components in timeseries
added 36 characters in body
Jan
27
comment Detecting components in timeseries
Thanks for the update this looks great now.
Jan
27
revised Detecting components in timeseries
added 144 characters in body
Jan
27
comment Detecting components in timeseries
I'm reading the pdf on the Bayesian Change Point detection in R, this is a great resource, thanks!
Jan
27
revised Detecting components in timeseries
added 161 characters in body
Jan
27
comment Detecting components in timeseries
Is there a way to flatten out the discontinuities at {517, 539, 596, 632} and at {2218, 2237, 2368, 2392, 2708, 2735} so that the graph looks more like @dr.belisarius's graph? And in general there many be many more plateaus not just the two means, but n means, will your approach work for that too?
Jan
27
awarded  Nice Question
Jan
27
comment Detecting components in timeseries
How and how did you know to divide by 10?
Jan
27
comment Detecting components in timeseries
This is a beautiful answer! How to I get the x values where it jumps?
Jan
27
comment Detecting components in timeseries
Nice work, but I'm still wondering how to find the x points 1k and 2k where the boundaries are?