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

learn more… | top users | synonyms

0
votes
0answers
27 views

How to handle the error of glmnet package for non-positive lambda?

I'm using glmnet package to learn regression models,it works fine, but for some models, I face an error and my script stops running. Here is my effort: ...
2
votes
2answers
54 views

Cluster Data based on Distribution

I have a list of diseases for my research. For each disease, I have a list of ages for the diseases. "Breast Carcinoma" may be a list of [1,2,2,3,4,5,5,5,5,5] while "Adrenal Cortex Neoplasms" maybe be ...
2
votes
1answer
59 views

Is there a decision-tree-like algorithm for unsupervised clustering?

I have a dataset consists of 5 features : A, B, C, D, E. They are all numeric values. Instead of doing a density-based clustering, what I want to do is to cluster the data in a decision-tree-like ...
2
votes
1answer
39 views

Having a Neural Network recreate what it's learned

I've created a basic Neural Network that learns from basic information and can verify whether or not a piece of information matches it's parameters from a match percentage. Conceptually however, I ...
0
votes
1answer
48 views

Comparing topic distributions between corpora using Latent Dirichlet Allocation and R topicmodels or python gensim

So I am working on a problem where I want to extract a set of LDA topics from one corpus, and then compare the distribution of those topics in other corpora. So basically I want to lock-in the topics ...
0
votes
1answer
44 views

Machine Learning on Percent/Continous Dependent Variable

I have a large dataset of 30,000 cases with 150 variables. I am looking for a few possible machine learning solutions/methods that I could try and use for cross validation. My dependent variable ...
0
votes
0answers
20 views

Association Rules “with a kind of class”

I want to use/adapt a recommendation algorithm for posters in an e-commerce. The thing is that I want to use previous categories searched before posting in a particular category (has to be at a very ...
1
vote
0answers
30 views

Machine learning with weighted / complex survey data

I have worked a lot with various nationally representative data. These data sources have a complex survey design, so the analysis requires the specification of stratification and weight variables. ...
0
votes
0answers
13 views

LMS cost function vs cross entropy cost function in neural networks

What is difference between using various cost functions: LMS,Cross entropy in neural networks? All of them have same derivative w.r.t final activation and hence all the gradients are still gonna ...
0
votes
3answers
78 views

What is shallow architecture in machine learning?

What is a precise definition of shallow architecture in machine learning?
0
votes
1answer
111 views

Intuitive explanation of Bayesian logistic regression?

I'm looking for an intuitive explanation of Bayesian Logistic Regression (I'm using it for texts if that's relevant). It seems that this article presents it, but it's, uh, way too mathy. Thanks!
4
votes
2answers
138 views

Why does PCA maximize variance of the projection?

Christopher Bishop writes in his book (Pattern Recognition and Machine Learning) a proof, that each consecutive principal component maximizes the variance of the projection to one dimension, after the ...
1
vote
0answers
17 views

How to combine n confusion matrices

Suppose you have $n$ confusion matrices, each from a different independent classification on a dataset. Suppose each classification is ran on a proper subset of the dataset, and usually these subsets ...
0
votes
0answers
42 views

Machine learning from implied variables

I have a situation where we are detecting anomalies based on data implied from the table data. As an example, I have data on registered individuals spending time on the portal. Based on this, I have ...
0
votes
1answer
93 views

tanh activation function vs sigmoid activation function

tanh activation function is nothing but 2*sigmoid - 1. Does it really matter between using those two activation functions. Which function is better in which cases?
0
votes
0answers
36 views

The correct way to do Cross-Validation

Consider the case that I need to do cross-validation for SVM to obtain a good estimate of the cost parameter $C$. I am not sure when should I divide the data into $K- $ folds. To perform the ...
1
vote
1answer
61 views

Original source for the “play tennis” dataset

A famous toy example in machine learning, especially with learning decision trees, is the well known "play tennis" dataset. Is there an official source for the dataset which could be quoted in ...
0
votes
2answers
41 views

Using machine learning to tell apart users from crawlers

Would it be possible to build anomaly detection algorithm to be able to tell apart real user from crawlers/spiders with high confidence? I have access to user tracking data where information about ...
1
vote
0answers
12 views

Prioritization based on three factors

Background: Sales reps visit doctor and detail about a product/drug. One visit is termed as one call. In return he writes the prescriptions to doctors prescribing that particular drug. Problem ...
1
vote
0answers
47 views
1
vote
0answers
46 views

How is L2 Boosting Different from a Big Regression Tree?

I'm learning about boosting. I think I understand how adaptive boosting works for classification. I'm trying to get some intuition for regression boosting. At each iteration, adaptive boosting ...
0
votes
1answer
43 views

What are the general strategies in creating a Probabilistic Graphical Model?

While there is lot of theory and probability in the background to understand, I wanted to know if there are any resources/quick pointers on what to consider while modeling a problem using Bayesian ...
4
votes
2answers
102 views

Linear PCA versus Linear Kernel PCA

Sources and definitions: PCA: http://en.wikipedia.org/wiki/Principal_component_analysis KPCA: http://en.wikipedia.org/wiki/Kernel_principal_component_analysis My question: If in KPCA i choose a ...
0
votes
1answer
21 views

Computing predicition intervals with cross-validation?

I'm using a k-fold (10-fold) cross-validation while building a model. I'm only using it to get an estimate of the out-of-sample error, not to pick a model from candidates. For example, if I have 30 ...
0
votes
0answers
37 views

A question about Latent Dirichlet Allocation model

when I used LDA model in my project, the result topic terms vary with the random seed. how to solve this problem ? thanks
0
votes
0answers
20 views

Time and space complexity of Deep Belief Nets (DBN)

What is the time and space(memory) complexity of DBNs? given d:number of dimensions(attributes), n:number of records, and l:number of hidden layers.
0
votes
3answers
22 views

What are the general strategies in creating a Probabilistic Graphical Model?

While there is lot of theory and probability in the background to understand, I wanted to know if there are any resources/quick pointers on what to consider while modeling a problem using Bayesian ...
0
votes
0answers
64 views

SVD application for a Boolean sparse Matrix

Basically, I am trying to have a recommender system based on SVD for a Boolean utility matrix. ie If at all some entries are present in the utility matrix, they will be 1 (I made it pseudo-implicit ...
1
vote
2answers
57 views

SVM parameter dependence on number of samples

I need to do a grid search to optimize SVM parameters gamma, C and epsilon (svm from e1071 r package). The problem is that I have a fairly large data set, about 100000 rows and 40 variables. I have ...
0
votes
1answer
31 views

Correlation coefficient for sets with non-linear corelation

What method can I use to test if there is a correlation between two sets of data? The correlation coefficient works if there is a linear association, but if I have two sets that are clearly (visually ...
0
votes
0answers
30 views

Build corpus with phrases

I have my documents as: doc1 = beautifull, very good, very bad, you are great doc2 = very bad, good restaurent, nice place to visit I want to make my corpus ...
0
votes
0answers
40 views

Correct methodology to repeat testing of classifier to get good estimate of performance

I'm having trouble with a basic machine learning methodology question. I understand the concept of not using the same data to both train and evaluate a classifier, and furthermore when there are ...
0
votes
1answer
39 views

A way to use GPU hardware in matlab [closed]

I know that theano is a python library for using gpu hardware and make effective implementations. Is there any such library or a way to do the same in matlab?
0
votes
0answers
22 views

$\nu$ SVM in terms of C-SVM

I have an implementation that solves the $C$-SVM optimization problem. Is it possible to use this algorithm to create a $\nu$-SVM? I know there is a connection saying $\nu$-SVM leads to $\rho ...
0
votes
0answers
39 views

Difference in values of tf-idf matrix using scikit-learn and hand calculation

I am playing with scikit-learn to find the tf-idf values. I have a set of documents like: ...
0
votes
0answers
24 views

Supervised classification on different time series

I have 300 files, each file has a time series data with a class label(0 or1) for each data point.I want to build a classifier, which can predict the class of a new time series data. How should I ...
2
votes
2answers
55 views

Split train//validation/test sets by time, is it correct?

Here's the scenario, slightly altered to a common one. Credit card fraud, payments for the last 12 months (a rolling window). Train with the data from the first 10 months, validate with data from the ...
0
votes
0answers
19 views

clustering versus projection - what are the best example/scenario to explain their differences

I am dealing with non statistician who know are crunching data but don't have a deep understanding of statistics. I am trying to introduce them to non-matrix factorization methods but it has been ...
2
votes
1answer
125 views

Predictive Modeler: How can learning Python and/or Java benefit me?

On a daily basis, I build predictive models (namely, logistic regression and credit scorecard models) using fairly large datasets (typically ~500k records and ~1k candidate variables) to predict ...
0
votes
1answer
64 views

How to approach a real machine learning problem?

As a ML beginner, I don't how to begin with this problem, or more generally, are there any typical steps to take when approaching a real problem? If I have some domain relevant knowledge, then I ...
0
votes
1answer
64 views

Question on Machine Learning Overview?

I am a researcher from India and working in the field of Computational Linguistics for quite some time. I have lately started working in the field of Machine Learning based algorithms. To do this I ...
3
votes
1answer
46 views

Difference in tf-idf values in R

I am playing around in R to find the tf-idf values. I have a set of documents like: ...
3
votes
1answer
310 views

Choosing the right forecasting technique

I'm currently attempting to forecast visitor data for stores. My dataset includes daily visitor totals of three years. Note that the dataset isn't complete (stores can be closed for a few days, etc). ...
2
votes
0answers
50 views

Emotion recognition lip zone processing

I want to detect emotions by comparing the cropped lip zone with different templates and output an emotion based on the score. So far I've applied: Normalization Discrete and fast Fourier transform ...
1
vote
1answer
60 views

Create a matrix of tf-idf values from documents

I have a set of documents like: D1 = "The sky is blue." D2 = "The sun is bright." D3 = "The sun in the sky is bright." and a ...
0
votes
0answers
32 views

Examples for commercial applications of data mining in pharmacy

I've always heard that data mining and machine learning tools/techniques are heavily used in the pharmacy sector and biology but I have never heard of companies that offer commercial applications of ...
3
votes
1answer
70 views

Understand the reasons of using Kernel method in SVM

I understand that one can use kernel functions (i.e. radial kernel) to create non-linear decision boundary. However, there is something with my logic and I am sure there is something that I clearly ...
2
votes
0answers
46 views

How to calculate accuracy of each feature

I read some paper (* about predicting user retention in StumbledUpon) and saw the authors provide a list of features with accuracy of each feature with the following explanation: As decision ...
2
votes
1answer
19 views

SVM Training: Working Set Selection

This is related to Joachims's 1998 paper on training SVMs (link to paper). In 11.3, I understand how the term $V(\mathbf d)$ arises as a result of a first order approximation, and why it needs to be ...
1
vote
2answers
76 views

ML & AI - Algorithm recommendation for “optimization by tuning parameters”?

As a newbie in Machine Learning (ML) and Artificial Intelligence (AI), I am here to ask some general algorithm pointers on my following question, which I have simplified into a very generic question. ...