KyBe
  • Member for 6 years, 9 months
  • Last seen more than a month ago
Unsupervised image segmentation
5 votes

Fast answear Mean Shift LSH which is an upgrade in $O(n)$ of the famous Mean Shift algorithm in $O(n^2)$ well know for its image segmentation ability Some explanations If you desire a true ...

View answer
Computational aspects are typically ignored by statisticians
Accepted answer
3 votes

I think what the author is speaking about is the time/memory complexity of algorithms that statisticians may don't care about. Make a model which is mathematically well proven may be more important to ...

View answer
Exponential runtime on distance matrix
1 votes

For 2 tables of size $n$ and $m$, join operation complexity is in $O(n.m)$ in worst case. If $n=m$ we are facing a quadratic operation which is why you observe slowness with the increase of tables ...

View answer
What is slowing down classic DBSCAN algorithm
1 votes

As @Anony-Mousse pointed it, on DBSCAN index structures are often used in order to decrease execution times. K-d-trees are one example but this one works well just in small dimensions. You had right ...

View answer
Spark Scala alternative Machine Learning Library?
1 votes

Broadcasting your data and learn on it with different learning parameters per spark partition is a solution only if your data isn t so big it can fit in each machine memory. If you desire apply ML ...

View answer
Agglomerative Clustering without knowing number of clusters
1 votes

If you don t know the number of clusters, i encourage you to look at those density based algorithm : Mean Shift, DBSCAN, OPTICS. They don t presume of the cluster number and are able to find random ...

View answer
Scala RDD operation
1 votes

For the first you can do as follow : val discount = salesdata.map( str => str.split(",")) .map( array => (array(0), array(1), array(2), array(3).toDouble) ) ...

View answer
K-means clustering with categorical data
0 votes

If you have exclusively binary variable you can use KModes, if you have both real and binary variables I would consider the KPrototypes algorithm. KModes use by default the hamming distance and ...

View answer
Supervised clustering
0 votes

KNN algorithm is a solution but it doesn't scale well. Cost of KNN is $O(n.log(n))$ per request if you made $n$ ones it become $O(n^2.log(n))$ and don't scale at all. It is applicable if your cluster ...

View answer
Question About Coming Up With Own Function for Distance Matrix (For Clustering)
0 votes

As @Anony-Mousse remind it, compute a similarity matrix is note applicable to large dataset. Memory complexity is linked to time complexity, if you want to read or writte $n$ value you will require at ...

View answer
Mixed types of data for clustering
0 votes

As @Anony-Mousse specify it you need a distance function fitting with your data nature. You have multiple possibilities, convert all your data as categorical, more specifically as binary data ...

View answer
Clustering algorithms for high dimensional binary sparse data
0 votes

If you know the ground truth of data, the ethnic here. You can visualize your binary cluster as follow. Compute prototypes of each cluster using majority vote per feature which has a linear complexity ...

View answer
Keras Loss Function for Multidimensional Regression Problem
0 votes

I fall on same issue with RMSE which by the way may be a good complementary choice of MAE. Thus in order to measure error prediction on multidimentional output the way i implemented was as follow. ...

View answer
Multidimensional regression in Scala
0 votes

A regression technique that allow to predict a multidimensional output can be the PLS ( partial least square ). I implemented it in scala and it will be soon available on Clustering4Ever repo. In fact ...

View answer
How would you categorize email subjects to find similar emails?
0 votes

You can associate the right semantic to each letter, start with the definition of the semantic. Build your model from scratch, use rigor to moove on forward. At this point you have the semantic of ...

View answer