Methods and principles of building "computer systems that automatically improve with experience."

learn more… | top users | synonyms (1)

2
votes
1answer
61 views

Choice of an evaluation metric for a graph clustering algorithm

I have instances for which the only thing I know is 70% of the distance matrix. I know some of these points form groups of correlated points (each point of a group is "close" to every point of the ...
1
vote
0answers
158 views

Machine Learning : Classification algorithm for very high dimensional data which is uniquely definable in a very small sub-space

I am new to machine learning, so forgive me if i am doing something absolutely absurd. I have a classification task (~100 classes) and have about 2 million training data points in a 2000 dimensional ...
4
votes
1answer
184 views

gaussian mixture model - approximate a matrix

I have a similarity matrix M - the value M(i,j) indicates the similarity between two elements i and j. I want to approximate that matrix using a Gaussian Mixture model or I want to cluster that ...
3
votes
2answers
430 views

Using the gap statistic to compare algorithms

I want to compare the performances of two clustering algorithms that give me different numbers of clusters. I recently learned about the gap statistic. However, from what I have learned, this ...
1
vote
2answers
137 views

How to report a SVM model to a 3rd party after cross-validation?

I have a binary classification problem. I trained my dataset using a Support Vector Machine (SVM). Now I want to report the model I trained to a 3rd party so that they can use. For the primal probem ...
1
vote
1answer
196 views

General questions regarding text-classification

I'm new to Topic Models, Classification, etc… now I'm already a while doing a project and read a lot of research papers. My dataset consists out of short messages that are human-labeled. This is what ...
5
votes
2answers
380 views

Can machine learning find all sort of crazy connections?

If you try a real thoroughly won't a computer find all sort of silly patterns? Messages from ETs in the bible rainy Sundays in China or Australia -> the chances of your sport team win reading many ...
0
votes
0answers
52 views

Which algorithmic approach is best for this problem

I have a problem where I get data from 3 different sources s1, s2, s3, and I have the target (value). I might have missing values from some of the predictor variables at certain rows. This is the ...
4
votes
2answers
142 views

Maximize sum of f(x), where f(x) is unknown, but we learn as each x is chosen

Let's suppose that I have a function like below, but I don't know what it is. However, as I choose x, I know what corresponding ...
-1
votes
1answer
161 views

Journals in statistical learning / machine learning [closed]

Can you please name some major and minor journals publishing articles in the field of statistical learning / machine learning. regards Anthony
0
votes
2answers
321 views

Machine Learning with Skewed Classes in R

I am looking for some suggestions on what methods are appropriate for training a dataset with a high skew in the outcome classes. The ratio of Class 0: Class 1 is about 20:1 and I am looking to ...
0
votes
0answers
56 views

Which diffusion of latent Dirichlet allocation is helpful for assign the words corresponds to each topic?

In my corpus documents I have two different subjects. Which diffusion of LDA (asymmetric or symmetric) could help for assigning the words corresponds to Subject 1 and Subject 2 in my Topics? Here is ...
0
votes
2answers
150 views

Will Multivariate Gaussian classifier work for text classification?

So far i have evaluated mn Bayes and Bernoulli, so my question is if i take the counts of the words of each document and use them for assigning the document to the particular class will it work with ...
0
votes
1answer
88 views

Classifier weighted towards recall?

I have a classification problem where getting true positives is much more important than true negatives. To be clear, I know that roughly 10% of my population are actual positives, but I can assign ...
0
votes
1answer
195 views

How to define silhouette for one cluster?

I want to compare two clustering algorithms. I took data that the first algorithm gathered in one cluster. The second algorithm gave 3 clusters for the same points. In order to compare the results, I ...
3
votes
2answers
1k views

How exactly to partition training-set for k-fold cross validation on multi-class dataset?

Cross validation is one of the most important tools because it gives us an honest assessment of the true accuracy of our system. In other words, the cross-validation process provides a much more ...
1
vote
3answers
542 views

Scalability of Markov Clustering

I want to do graph clustering on a large dataset (A graph with 600,000 Nodes and tens of millions of edges). I read about Markov clustering. I saw this algorithm involved the calculation of a ...
-2
votes
1answer
102 views

k-medoids algorithm with incomplete distance matrix

I want to apply k-medoids algorithm using an incomplete distance matrix as input. How can I handle the lack of information of this matrix? Just ignoring the missing distances? Or is there a better ...
1
vote
1answer
148 views

k-core clustering algorithm

I am trying to cluster data. Each point in this dataset is connected to some other points. I want to define clusters "depending on how much the points are connected to each other". After some ...
0
votes
0answers
79 views

What can be a cause of a extremely high standard coefficient?

I am using RapidMiner to perform linear regression with ridge parameter 1$\text{E}$ -8, min tolerance 0.05 and M5 prime for feature elimination. The std coefficient ...
0
votes
0answers
43 views

Correlating ranked lists

Let's assume I have 10 users who rank a list by preference. A B C etc. My questions are: What is the best statistical method to find which lists are the most correlated? If they are the same, ...
4
votes
2answers
496 views

How to set the step size for stochastic gradient descent such that its provable it will converge

Recall stochastic gradient descent (for regression): $\theta = 0 $ $ \text{Randomly select } t \in [1,n]\{\\ \quad \theta^{(k+1)} = \theta^{k} + \eta_{k}(y^{(t)} - \theta \cdot x^{(t)})x^{(t)}\\ ...
7
votes
1answer
133 views

Linear regression closed form solution and having enough training points

I was trying to understand better when we can learn a unique parameter for linear regression and how much data is required to get one. Say that we want to learn a parameter $\theta$ such that ...
3
votes
0answers
72 views

Machine learning with ordered labels

The usual method for adapting binary classifiers like various SVMs to multilabel data is one-vs-all, which assumes that labels are independent and in case of a prediction error we don't care what ...
1
vote
0answers
45 views

Random initialization with k-means clustering

I read on my machine learning course (on coursera) that random initialization performed several times and then taking the cluster with the lowest cose could help when the number of clusters is ...
1
vote
2answers
143 views

What does the term “Estimation error” mean?

I was reading some notes on machine learning when I came across the following sentence: First, we may have a large estimation error. This means that, even if the true relationship between x and ...
4
votes
1answer
105 views

Do fewer support vectors imply a simpler model?

I am applying $\epsilon$- and $\nu$-regression to sample data, and I discovered I had different results in terms of the count of support vectors. When I have fewer support vectors, does it mean that ...
0
votes
0answers
35 views

Evaluate collisions in classification problems

Short Introduction In a classification problem, the objective is to identify to which of a set of categories a new observation belongs, on the basis of a set of examples whose category membership is ...
5
votes
1answer
560 views

Evaluating a regression model's performance using training and test sets?

I often hear about evaluating a classification model's performance by holding out the test set and training a model on the training set. Then creating 2 vectors, one for the predicted values and one ...
1
vote
0answers
925 views

Multidimensional scaling using Python

I have 6,000 points for which I have all pairwise distances in a distance matrix. I want to get an idea whether these data were generated by a mixture of Gaussian distributions so I'm trying to get a ...
1
vote
0answers
89 views

How to extract structured information from a text string?

I have a text string containing unstructured data and I would like to analyze it in order to extract structured information. In particular, this text string specifies when a service is operational ...
0
votes
1answer
442 views

Beginner - How can I use ranked values in my Logistic Regression?

I am running a Logistic Regression on some data to predict if a webpage is "good" or "bad". I got the dataset from a finished Kaggle competiton here (train.tsv). I extract the second column of this ...
2
votes
2answers
432 views

Scaling the backward variable in HMM Baum-Welch

I am just trying to implement the scaled Baum-Welch algorithm and I have run into a problem where my backward variables, after scaling, are over the value of 1. Is this normal? After all, ...
3
votes
3answers
140 views

Examples of machine learning in personal computers [closed]

Are there any examples of machine learning in our PC's? The only one that I know is Windows Speech Recognition application. I do not mean any add-ons. I mean any basic applications that are ...
1
vote
1answer
76 views

Divergence measure of two classifiers' performance?

I have two classifiers built with the same data. How can I measure divergence of these models? I found something like DIC but I don't know how to calculate this in R?
2
votes
2answers
321 views

Example how maximizing and minimizing a function can be equivalent?

I don't understand how sometimes given an optimization problem, a function could get its optimal solution by minimizing or sometimes just by reformulation it becomes maximizing. Can you please give me ...
0
votes
2answers
104 views

Minimizing the norm of a vector of parameters

I'm reading a paper that defines a function $f_w(x)$ that takes input $x$ and parameters $w$ and a set of constraints. There are also training data. The aim is to find the set of parameters $w$ that ...
0
votes
1answer
393 views

Goldfarb Idnani quadratic solver

I am implementing the Support Vector Regression (SVR) algorithm by means of quadratic programming. In order to do that, I am using an optimization library that contains a quadratic solver based on the ...
3
votes
1answer
87 views

Evaluation of probabilistic predictions

In the 2010 KDD cup, participants were tasked with estimating the probability that a student would solve a particular exam question. The competition winner was whoever produced the lowest root square ...
1
vote
1answer
86 views

Simple question about multivariate/multiclass classification

From this link Text Classification using Naive Bayes, there are two models described for classification, Naive and Bernoulli. My question is if i want to make this classifiers for multiclass ...
2
votes
1answer
85 views

What does “aspect model” refer to in machine learning

Hopefully this is the right place to ask my question. I am reading this paper about cold-start recommendations: http://dl.acm.org/citation.cfm?id=1352837 the expression "aspect model" is used a lot ...
7
votes
1answer
2k views

Selecting an appropriate machine learning algorithm?

I do not think that this is a difficult question, but I guess someone needs experience to answer it. It is a question that is asked a lot here, but I did not found any answer that explains the reasons ...
0
votes
0answers
39 views

Does smoothing of Bayes classifier will increase precision?

I have implemented Bayes multinominal and Bernoulli's model and my question is does the smoothing have any impact of the performance of both models (Laplace’s law of succession or add one smoothing)?
7
votes
3answers
713 views

Can you compare different clustering methods on a dataset with no ground truth by cross-validation?

Currently, I am trying to analyze a text document dataset that has no ground truth. I was told that you can use k-fold cross validation to compare different clustering methods. However, the examples I ...
0
votes
1answer
239 views

tf-idf in multi-label classification task

I have a question regarding application of tf-idf. Let's assume I have a document classification task, there is a training set of documents that are multi-labeled, such that one document can have ...
1
vote
1answer
196 views

Intuition on learning rate or step-size for perceptron algorithm

Recall the perceptron algorithm: cycle through all points until convergence $\text{if }\, y^{(t)} \neq \theta^{T}x^{(t)} + \theta_0\,\{\\ \quad \theta^{(k+1)} = \theta^{k} + y^{(t)}x^{(t)}\\ \}$ ...
2
votes
1answer
379 views

When using a Neural Network to classify more than two classes, is it better to have multiple output nodes (one for each class) or one output node?

Currently, I am using a neural network to classify data into one of three groups (a logistic activation function is used on all but the output nodes). I can train the neural network in two ways: 1) ...
3
votes
1answer
104 views

libsvm_linear kernel_increasing C value

I'm using libsvm in C-SVC mode (-s= 0) with linear kernel (-t= 0), and I'm required to train multiple SVMs( I have four classes). My training and test sets have the same number of instances and ...
4
votes
2answers
181 views

ROC graph interpretation

I'm reading Fawcett's 2004 paper on ROC graphs for machine learning algorithms, which can be found here. On page 7-8 he shows a simple ROC example and makes some interpretations that I don't ...
5
votes
3answers
770 views

Is a lower training accuracy possible in overfitting (one class SVM)

I am using the heart_scale data from LibSVM. The original data includes 13 features, but I only used 2 of them in order to plot the distributions in a figure. Instead of training the binary ...