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

learn more… | top users | synonyms (1)

0
votes
2answers
12 views

Prediction of features given predictor

I am working on a problem where my objective is to predict y given some features x1,x2,x3,...x8,x9 I solved this problem using some statistical and machine learning techniques like regression, trees, ...
1
vote
1answer
38 views

Relation between variance of eigenvalues and the effectiveness of PCA on the data

If the covariance matrix has eigenvalues $$\lambda_1 \ge \lambda_2 \ldots \ge \lambda_d > 0,$$ why is the variance of the eigenvalues, $$\sigma^2=\frac{1}{d}\sum_{i=1}^d (\lambda_i-\bar ...
0
votes
0answers
18 views

ParagraphVector od doc2vec for classification tasks [on hold]

I am really interested to use doc2vec on classification task. I'dont understand how they create the featurevector for classification. I am trying to sum all words and paragraph id of the sentence to ...
1
vote
0answers
14 views

Support Vector Machine image classification in R

I'm looking for some direction for creating/running a support vector machine (SVM) classification on a multi-band Landsat image in R. What I have: Landsat 8 image with 8 bands plus a NDVI, and ...
9
votes
2answers
715 views

Introduction to machine learning for mathematicians

In some sense this is a crosspost of mine from math.stackexchange, and I have the feeling that this site might provide a broad audience. I am looking for a mathematical introduction to machine ...
0
votes
0answers
21 views

Feature selection for logistic regression [on hold]

Not sure if the feature selection is the correct term but assuming I have data x,y | z where x and y features and z is target. And the task is to classify z using x,y but I know that data is not ...
1
vote
0answers
16 views

How to merge different predictive models training with different data sets?

Is there any good method to merge/consolidation different predictive models which were trained on different features but outputs the same goal. Example: Model 1 with features a + b + c (trained on ...
0
votes
1answer
30 views

Buiding Ensemble model

I'm new to ensemble model. Suppose I've KNN models like this - (in R) library(class) ...
0
votes
0answers
7 views

Importance of the norm of the weight vector in the perceptron algorithm

I have exhausted all possible searches online on the role of the norm of the weight vector in binary classification. The only information i am getting is that it prevents over-fitting. I don't see how ...
0
votes
0answers
10 views

How to include only true positives and false positives, that is ignore false negative classifications in a confusion matrix?

I have performed a 10 fold cross validation on my data set using binary decision trees. I've got 6 trees (to detect one of the six basic human emotions from facial data points) trained for each fold. ...
0
votes
0answers
18 views

Find repetitive patterns in matrices below

How can I identify the repetitive patterns from the matrices below? My problem is that the patterns in the matrix are different from matrix to matrix (dependent on the input data). I need some machine ...
1
vote
0answers
13 views

Apply trained MDS model to new data

I have both a distance matrix and the original vectors, and am using MDS (Multidimensional Scaling) with R to generate vectors in more dimensions for the data. With dimensionality reduction (for ...
4
votes
1answer
29 views

How to train a model when instead of a target we have a range where it is?

Often in machine learning we have a situation when target is numeric (real or integer). Each target comes with an associated input vector. The goal is to learn the mapping from the input vectors to ...
2
votes
1answer
47 views

Manifold learning: does an embedding function need to be well behaving?

I am trying to learn about manifold learning techniques; a family of methods in machine learning. According to this idea, there is a low ($d$) dimensional, hidden space where the real data generation ...
0
votes
0answers
25 views

Incorporating metadata to a supervised Topic Model

I have texts and their metadata and a response variable (how many times the text has been read). I'm interesting in finding out how the latent topics in the set of texts are related to the popularity ...
3
votes
1answer
56 views

What is “Prediction Accuracy (AUC)”, and how is it the number conducted in Machine Learning?

Here is the link in question: http://applymagicsauce.com/documentation.html When the Cambridge University Psychometric Center's "Apply Magic Sauce" defines how their ...
0
votes
0answers
17 views

machine learning to extend a matched sample (sanity check)

I'm a bit new to machine learning, but I want to try to use it in a project I'm working on. Specifically, I'd like to use it to identify a sample of potentially rare events. I'm not entirely sure if ...
1
vote
1answer
29 views

How could the predictive mean in a GP become negative when both the prior and the training target values are non-negative?

I am training a Gaussian process regression where the training target values are between 0 and 1 and the prior mean is the fixed zero function. The predictive mean sometimes becomes negative e.g. ...
0
votes
1answer
56 views

Which library is the easiest to start with for Deep Learning

I am quite proficient with Machine Learning libraries and now want to get into Deep Learning. I am even quite comfortable with neural networks as far as understanding back propagation algorithm is ...
1
vote
0answers
35 views

Combining bootstrap and cross validation

I recently read this paper: Estimating misclassification error with small samples via bootstrap cross-validation, by Fu et al. (BMC Bioinformatics, 2005). The authors talk about combining cross ...
2
votes
0answers
47 views

Combining two probabilistic predictions

I am solving a machine learning task in which I need to predict a label $\tau$ from input $\vec x$. The input $\vec x$ can be considered as two parts $\vec u$ and $\vec v$ ($\vec x$ can be thought of ...
0
votes
0answers
332 views

What does mean by PAC learning theory

I am new in machine learning field. I am studying a course of machine learning(standford university ) and I did not understand what's mean by this theory and what its utility. I am wondering if ...
0
votes
0answers
3 views

Are the IREP and RIPPER algorithms considered Inductive Logic Programming? [migrated]

When you look at articles discussing Inductive Logic Programming (ILP) they mention approaches like FOIL, Golem and Progol. They don't mention any of the rule learning algorithms like IREP or ...
0
votes
0answers
34 views

How to determine the accuracy of regression? Which measure should be used?

I have problem with defining the unit of accuracy in a regression task. In classification tasks is easy to calculate sensitivity or specificity of classifier because output is always binary {correct ...
0
votes
0answers
25 views

What do you do with outliers when developing statistical models?

I am a beginner so I have an extremely tough time dealing with outliers. I wanted to ask the community to help me understand rule of thumbs or anythng that would help me deal with these questions ...
2
votes
1answer
36 views

Validation of machine learning algorithms implementation

What are some techniques by which we can verify that a current implementation of a machine learning algorithm is correct? Is using the results of a benchmark dataset is enough?
0
votes
0answers
30 views

trouble with understanding neural network

Can anyone give an explanation for a page 422 from the The Elements of Statistical Learning. I couldn't understand the meaning of 'the least constrained model.' Paragraph and picture is shown as ...
1
vote
0answers
21 views

How do I learn algorithmic trading? [on hold]

How do I learn how to set up an algorithmic trading system? I have taken Andrew Ng's Machine Learning course and am completing data sciences specialization on Coursera, am familiar with R and Octave. ...
0
votes
1answer
37 views

Why does hypothesis of SVM output 0 or 1?

Prof. Andrew Ng in his Machine Learning class says that unlike Logistic Regression, SVM outputs hypothesis as 1 or 0. But I don’t understand why SVM's behavior differs from that of logistic regression ...
0
votes
0answers
26 views

k-NN classifier with a data-dependent distant measure?

As we know, in a $k$-NN classifier, we have to define a distance measure. Imagine a case where I use a certain dimensionality reduction technique to project my high-dimensional data to 2D, and then I ...
0
votes
0answers
15 views

Test for autocorrelated variables

I would like to know if there is a good non-parametric test for detecting auto-correlation of one variable between all the observations of my dataset. I have 60 predictor variables for a statistical ...
3
votes
1answer
27 views

How to make a trained neural network “forget” an instance?

I am using neural networks for predicting the behavior of a dynamic system. A neural network is trained online using snapshots from the system's past. The system changes its state at irregular ...
0
votes
0answers
12 views

Anomaly Detection with very small number of positives [closed]

I am trying to detect anomalies in a population comprising of 10 features and around 90,000 observations. Past investigations have revealed 18 positives. Given limited data for supervised learning, I ...
4
votes
2answers
71 views

Is dimensionality reduction almost always useful for classification?

Is singular value decomposition almost always useful in practice for enhancing the predicative power of a trained classification model? E.x. A dataset for classification has 20,000 features. Run SVD ...
0
votes
0answers
32 views

using Cross Validation in matlab with neural networks

I want to make a cross validation on neural network, I tried to pass the labels to crossval function, with the help of ...
0
votes
1answer
25 views

What are the techniques to deal with classifying sparse categorical features?

Suppose I have a group of features each one is sparse with a few number of values (1-10) what are the required preprocessing steps required to avoid degradation of the performance of the classifier ...
1
vote
1answer
124 views

Machine Learning

I have been working on some self study "machine learning". Based on a few posts here, I wanted to make a program that "learned" via Bayes Law. I test it with some simple truth tables. It recalls the ...
3
votes
1answer
26 views

Cumulative match score

I have seen loads of graphs in papers of cumulative match scoring, but I can't find any information about what it means, or how it is created. A context that would be useful to see the explanation ...
0
votes
0answers
16 views

Generating a good training dataset for decision tree building

I am building a decision tree predicting the accuracy score of an image processing algorithm, based on a number of image parameters. I have identified 6 uncorrelated parameters that impact the ...
0
votes
0answers
24 views

Learning user behavior that changes over time

I am learning a model using SVM that will predict user behavior of some kind. Simplifying this model, each example in the feature space contains some features: $f_1,f_2,..,f_n$ and a class $a$ that ...
6
votes
1answer
37 views

Has there been a project to apply machine learning to generation of indices for books?

Generating an index for a textbook is a tedious task. Can one automate it with machine learning? Are there any references to previous attempts in the literature to do this?
0
votes
0answers
41 views

Semi-supervised classification with Rmixmod package in R

Semi-supervised classification with Rmixmod package in R. http://math.univ-lille1.fr/~biernack/index_files/articleJSS.pdf , a document on the Rmixmod R package, provides mathematical exposition of ...
1
vote
1answer
39 views

SVM in R (package e1071): predicting class using predict()

I have difficulties to understand predict.svm. Please find an illustration of my confusion below. As we can see, results are different depending on the ...
2
votes
1answer
36 views

Expectation Maximisation

I'm currently reading Thomas Hofmamms paper on Probabilistic Latent Semantic Analysis. He includes a formula for the E step in Expectation Maximisation, but has proposed an alternative to this step ...
4
votes
1answer
29 views

Zero-centering the testing set after PCA on the training set

I have a training set of data on which I do principal components analysis (PCA) and save the loadings/eigenvectors/coefficient matrix. I want to use the eigenvectors to transform my testing data into ...
0
votes
0answers
7 views

How do i get prediction accuracy when testing unknown data on a saved model in Scikit-Learn?

i have a model i have trained for binary classification, i now want to use it to predict unknown class elements. ...
0
votes
0answers
9 views

Blocks of variable size in k-fold cross-validation

I would like to make a custom k-fold cross-validation method for my data, by generating folds of auto-correlated observations. This would create many folds of variable size for test errors as well as ...
0
votes
0answers
8 views

Feature selection in GBM

I am using gradient boosting (caret package in R). As far as I understand, the feature selection is already included in this package. However, I slightly ...
0
votes
1answer
32 views

Using Adaptive Linear Neurons (Adalines) and Perceptrons for 0-1 class problems

I am wondering how to adjust the Adaline algorithm to classify the classes 0 and 1 instead of -1 and 1. I found a section in Neural Networks and Statistical Learning by Ke-Lin Du, M. N. S. Swamy ...
0
votes
0answers
18 views

Observation Likelihood in hidden Markov models

As far as I understand, in discrete HMM, the observation symbol probability distribution $b_{i}(O_{t})$ is always a probability less than 1, e.g. $\frac{1}{6}$ for each side when rolling a dice. But ...