| clear query|facets|time |
Search criteria: position.
Results from 21 to 30 from
68 (0.38s).
|
|
|
Loading phrases to help you
refine your search...
|
|
Re: Vector truncation for visualization - Mahout - [mail # user]
|
|
...On Thu, Jun 9, 2011 at 2:27 AM, Lance Norskog wrote: Yes. Not a random matrix. A matrix of positions shifted back to have average mean (aka PCA). exp(-r_ij ^ 2 / \sigma) is a common...
|
|
|
Author: Ted Dunning,
2011-06-09, 06:20
|
|
|
LSH notes on text documents - Mahout - [mail # dev]
|
|
... non-random distributions that make the default formulation of LSH very bad. The problem is that document vectors are normally confined to the positive orthant. That means that a random hyper...
|
|
... the requisite 50% probability of being positive for any document. ...
|
|
|
Author: Ted Dunning,
2011-04-25, 22:11
|
|
|
Re: Predictive analysis problem - Mahout - [mail # user]
|
|
...SMART indicators have limits. The generally have low false positive rates, but very high false negative rates. Put another way, if the alarm goes off, a failure is imminent, but many...
|
|
|
Author: Ted Dunning,
2011-09-11, 05:38
|
|
|
Re: "Geometric Random Hyperplane LSH" - simple implementation - Mahout - [mail # user]
|
|
... for positive orthant vectors. For oddly distributed vectors, it still might be good to use difference vectors as a basis for LSH, but I am much less convinced than before. On Sun, May 15, 2011 at 8...
|
|
|
Author: Ted Dunning,
2011-05-16, 05:35
|
|
|
Re: Relevance score - Classification - Mahout - [mail # user]
|
|
... documents that are labeled as positive and negative relative to the question of interest. In your application, you don't have training data of the sort to build the second kind of classifier so you...
|
|
|
Author: Ted Dunning,
2011-11-24, 07:31
|
|
|
Re: Mahout: NB Model for Text Classification - In Sample Error - Mahout - [mail # user]
|
|
.... In addition, it makes sense to also sample messages that have significant numbers of terms that do not appear in your positive training examples. These methods are much simpler than doing active...
|
|
|
Author: Ted Dunning,
2011-11-19, 07:46
|
|
|
Re: confidence values of one (or more) feature(s) - Mahout - [mail # user]
|
|
... instance = encode(data, traceDictionary) Matrix b = model.explain(instance); ModelDissector md = new ModelDissector(); // get positive terms ModelDissector.update(b.getColumn(0), td...
|
|
|
Author: Ted Dunning,
2011-11-03, 20:24
|
|
|
[MAHOUT-557] Bug in Auc computation - Mahout - [issue]
|
|
...0 == tieScore)
Unknown macro: {
k0++;
i0++;
v0 = scores[0].get(i0);
}
// and how many positives
int k1 = 0;
while (i1 < n1 &...
|
|
... accessing it
while (i0 < n0 && v0 == tieScore)
Unknown macro: {
v0 = scores[0].get(i0);
k0++;
i0++;
}
// and how many positives
int...
|
|
|
http://issues.apache.org/jira/browse/MAHOUT-557
Author: Ted Dunning,
2011-05-21, 04:18
|
|
|
Re: LSH notes on text documents - Mahout - [mail # dev]
|
|
... values and the eigenvectors are just the e_i themselves. After transformation, all values are still in the positive orthant. I may have misunderstood what you are suggesting, but I don't think...
|
|
... functions is sub-optimal for data consisting of only positive values. On Mon, Apr 25, 2011 at 3:45 PM, Jake Mannix wrote: ...
|
|
|
Author: Ted Dunning,
2011-04-25, 23:08
|
|
|
Re: Logistic Regression Tutorial - Mahout - [mail # user]
|
|
...Yes. It does stand for area-under-(RO)-curve But the better definition is that it is the probability that a randomly selected positive example will have a higher score than a randomly...
|
|
|
Author: Ted Dunning,
2011-04-29, 17:54
|
|
|
|
