1
vote
0answers
19 views

How to proceed if a rule-based classification algorithm finds an instance that can be classified two ways?

I am training a rule based algorithm (PRISM or CN.2) with n classes (y_1,y_2,..,y_n). All rules in the training RuleSet are in ...
0
votes
0answers
24 views

Significance of a 1 state Hidden Markov Model

I've been training different observation sequences to obtain different HMMs corresponding to each observed data. Something intriguing is that I get one observation sequence represented by 1 state. ...
1
vote
0answers
46 views

Why does k-NN perform better than SVR and linear regression?

I have a data set used in a regression with 30 attributes and 30K instances. I am trying out a bunch of algorithms (SMO regression, Linear Regression and K-NN) but it was quite surprising to see that ...
4
votes
1answer
57 views

Using text mining/natural language processing tools for econometrics

I am not sure whether this question is fully appropriate here, if not, please delete. I am a grad student in economics. For a project which investigates issues in social insurances, I have access to ...
1
vote
3answers
87 views

Skewed data for regression analysis

I have 30 features in my self-collected dataset where I want to build a regression model. When I look at my data, most of the attributes (95% of the data points) are skewed on a very small range. Out ...
1
vote
1answer
62 views

Confusion about hidden Markov model

I've gone through Hidden Markov models (HMM) for the past few months. However there are a few things that are confusing. The set up is simple: I have to model some human gestures such as walking, ...
0
votes
0answers
35 views

How to build an automated Question/Answer system using machine learning techniques?

I would like to build an automated Q/A system using machine learning concepts. Would it be optimal to build this system using Bayesian network, simple if-else system, or something else more ...
0
votes
0answers
33 views

How do I check if there is overfitting in weka?

In weka, how do I check if an induced tree overfits the training data?
0
votes
2answers
33 views

Weka GUI - How to compare 2 classifiers after testing trained model?

I'm new to Weka (and machine learning) so this question would be a bit silly. So I have 2 models built using J48 and RandomForest (both run with 10-fold cross-validation mode) on a 40,000-tuple ...
3
votes
2answers
95 views

Why is k called representer of evaluation in the definition of kernel functions

Why is $k$ called representor of evaluation? From the book "Learning with kernels" by Bernhard Schölkopf we have the following lines (page 33): $\langle k(.,x),f\rangle = f(x)$, in particular ...
0
votes
0answers
30 views

time complexity and space complexity for HMM forward recursion

When Reading the HMM models, I found the following discussion on the time complexity and space complexity regarding forward recursion. I am sort of confusing on the reason of getting O(K^2N) and ...
0
votes
0answers
40 views

Appropriate method for supervised learning of small data set with few variables

What method exc. for regression can be used in order to get y=f(x1,x2) on a training set of 800 to 2000 samples? y is a whole number <0,15>, x1,x2 are real <0,40>? I'm interested in prediction ...
2
votes
0answers
62 views

SVM classifier (with soft-margin) implementation in R, gamma value and quadprog

I'm trying to implement a Support Vector Machine classifier in R and I have to solve the optimization problem using the quadprog R package which solves problems of the form : $$min_b \frac{1}{2} ...
0
votes
0answers
58 views

Today's popularity of main data mining and machine learning tasks

In my dissertation about clustering, I would like to start with showing how clustering is becoming more and more popular in recent years in comparison with other data mining and machine learning tasks ...
1
vote
0answers
11 views

Iterated Conditional Mode approximation in E step of EM

I wanted to know what is the mathematical justification for using ICM as an approximation for the E step in an EM algorithm. As I understand in the E step the idea is to find a distribution that is ...
2
votes
1answer
85 views

How to compare two datasets using metrics drawn from unknown distributions and with small sample sizes?

I have two datasets consisting of metrics from several experiments. Dataset 1 is the collection of results of experiments E performed by user A on product A, repeated N times. Dataset 2 is the ...
1
vote
1answer
33 views

Bias term in support vector machine

In SVM, there is a bias term. But looks to me there are very few discussions on the physical meanings of this term. Why should we have that? How does this term affect the model?
0
votes
0answers
36 views

How does R{MASS} lda function use MLEs to improve its result?

I am using the LDA function in the MASS package of R, which has the following specification: ...
1
vote
2answers
93 views

Highly unbalanced test data set and balanced training data in classification

I have a training set with about 3000 positive instances and 3000 negative instances. But my test data set is pretty much un-balanced. The positive set only has 50 instances and negative has 1500 ...
6
votes
2answers
116 views

Is there overfitting in this modellng approach

I recently was told that the process I followed (component of a MS Thesis) could be seen as over-fitting. I am looking to get a better understanding of this and see if others agree. The objective of ...
4
votes
1answer
111 views

Timeline of machine learning and data mining breakthroughs

Is there any timeline or historical overview of the most important breakthroughs in machine learning and data mining?
0
votes
0answers
27 views

coordinated dual descent method and sequential minimal optimization

Libsvm uses the sequential minimal optimization as its main solver while Liblinear uses coordinated dual descent method. What are the major differences between these two methods? Looks like both of ...
0
votes
0answers
59 views

How to identify a new pattern in a URL with a machine learning algorithm (Text mining)

I am trying to identify new patterns after analyzing a number of URLs. So let's say, I am investigating the hypothetical website Yoohle.com and their URLs have the following structure. domain = ...
0
votes
2answers
78 views

Normalizing SVM predications to [0,1]

I have trained an linear SVM which takes a pair of objects, computes features and is expected to learn a semantic similarity function between objects(we can say that it predicts whether the two ...
3
votes
3answers
189 views

How does PCA improve the accuracy of a predictive model?

I've seen in a kaggle challenge about digit recognition someone who used PCA before decision tree or other techniques. I thought it was just for compressing data but he aimed to improve his score. ...
0
votes
1answer
165 views

understanding of libsvm output

I applied libsvm to build a text classifier. The output looks like as follows: ...
0
votes
1answer
193 views

ROC curve and confusion matrix in classifier performance evaluation

I applied two different classifiers against the same validation set. It turns out that classifier A is better than classifier B in terms of ROC curve. However, classifier B is better than classifier ...
0
votes
1answer
95 views

Choosing a better data-set

I have two data-sets for same samples. But they are produced using two different instruments. I want to choose one data-set for further analysis. How can I find/prove which data-set is better? To ...
0
votes
1answer
99 views

Hidden Markov Model with MFCC coefficients

I don't know whether this is the correct forum for this but here goes: I'm trying to implement a Hidden Markov Model to be able to predict and find the best sequence/path for a training file. So ...
0
votes
1answer
112 views

How to create artificial data with one binary response variable?

I want to check various classification model like random forest, tree, knn,etc. I used some bench marking data set but now I need to simulate my own data set with a binary response variable.
-1
votes
1answer
72 views

Easy way to test usefulness of data for stock market analysis? [closed]

I have a lot of data (gigs) that may be useful in predicting equity prices. I can import these as a series of features (columns) in a table where the companies are rows. I have time series information ...
0
votes
0answers
58 views

the effects of feature matrix format on the training time of LIBSVM

I am using Libsvm to perform text classification tasks. I normally uses binary occurrence, TF/IDF to build feature set for the input documents. It normally takes quite longer for Libsvm to finish ...
1
vote
0answers
61 views

Determining optimal height for regression tree

I have a data set of approximately 400,000 records (for those of you who know, the data set is the one provided by yahoo for their yahoo learning to rank challenge). From this data set I learn a ...
10
votes
2answers
444 views

How far will self study get me?

I have never taken part in an official or structured data analysis or machine learning course (other than recent online offerings) and have learned most of what I know from reading and trying things ...
2
votes
2answers
125 views

Increasing the sample size does not help the classification performance

I am training a SVM classifier based on a given document collections. I started from using 500 documents for training, then I add another 500 for training, and so on. In other words, I have three ...
1
vote
0answers
167 views

Validation error less than training error — implications?

I am running a neural net to predict used car prices, sample size is 800. Using both 10-fold cross validation (10 times) and 1/3 holdback (10 times), the $R^2$ for training is about 0.60 and for ...
1
vote
1answer
195 views

Distant supervision: supervised, semi-supervised, or both?

"Distant supervision" is a learning scheme in which a classifier is learned given a weakly labeled training set (training data is labeled automatically based on heuristics / rules). I think that both ...
3
votes
1answer
138 views

Machine learning predicted value

When we fit a generalized linear regression (e.g., logistic regression, gamma regression) we are estimating the population average Y given the predictors $X$ ( i.e., $E(Y | X)$ ). When we fit a ...
3
votes
1answer
137 views

Variational inference for nested Chinese restaurant process

I recently read paper by Chong Wang and David M. Blei "Variational Inference for the Nested Chinese Restaurant Process". And I couldn't understand the next part (from p.5): The variational update ...
2
votes
0answers
67 views

Data Mining / ML applications in hydrodynamics?

I have a question about Scientific Data Mining. Do you know successful case studies of applying Data Mining / Machine Learning techniques in hydrodynamics? In general, does it make actually sense to ...
1
vote
2answers
105 views

Predictive Modeling question on Weka

I would like to predict the number of flu cases in the future using predictive modeling. I am very new to statistics, so I'm not sure which classifier to use in this case. For the attributes, I'm ...
4
votes
0answers
85 views

Regarding the sampling procedure in Adaboost algorithm

The AdaBoost algorithm states that it is to train a classifier based on the training data according to a weight vector. Assume the size of training data is N, the weight vector is of dimension N as ...
4
votes
1answer
89 views

Regarding redundant training data in building SVM-based classifier

To build a SVM-based classifier, I have a training data set consisting of N data points. Some of them are redundant. For instance, there have 50 data points which are exactly the same, and there have ...
2
votes
1answer
110 views

LDA topic models for various and unknown domains

We have a large collection (1-2M) of documents of various domains (politics, design, programming, etc.). And lets assume that we don't know the exact number of domains. And our goal is to build ...
2
votes
1answer
120 views

Modelling longitudinal data

We have longitudinal data on children(n<20) in which we measure different quantities A,B,C,D (like distance walked, time spent in school etc.). These are all continuous variables. We measure these ...
3
votes
2answers
309 views

training approaches for highly-imbalanced data set

I have a highly-imbalanced test data set. The positive set consists of 100 cases while the negative set consists of 1500 cases. On the training side, I have a larger candidate pool: the positive ...
3
votes
3answers
299 views

Regarding precision and recall for the highly unbalanced validation data set [duplicate]

Possible Duplicate: Optimising for Precision-Recall curves under class imbalance I built a classification model and tested it against a validation data set. The positive set is composed of ...
2
votes
1answer
120 views

R packages or open source software for training Hidden Markov chains

Are there any well-designed R packages or other open-source software for training Hidden Markov chains?
1
vote
1answer
54 views

some basic questions for process mining

Are there any good books and articles for introducing Process Mining? What are the state-of-the-art research results for process mining? What are the differences between process mining and time series ...
0
votes
0answers
103 views

What are the good algorithms for feature extraction for large dataset?

I have KDD dataset for detecting fraud actions on networks but it has millions of lines and >20 feature columns. Thus it is not viable to process all these on my personal computer. I am thinking about ...

1 2 3