Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [machine-learning]

Machine learning algorithms build a model of the training data. The term "machine learning" is vaguely defined; it includes what is also called statistical learning, reinforcement learning, unsupervised learning, etc. ALWAYS ADD A MORE SPECIFIC TAG.

1
vote
2answers
34 views

Define attribute importance in unsupervised learning [on hold]

I'm using 'NbClust' package to help me to get the "optimal number of clusters" and I noticed in my dataset I have attributes with different importance. I have 5 attributes: x1,x2,x3,x4,x5 and I know ...
0
votes
0answers
8 views

Can Conditional Random Fields(CRFs) become a discriminative model by changing partition function?

In Introduction to conditional random fields, page 24, equation (2.18) and (2.19), the linear-chain CRFs is defined as: $$p(y|x) = \frac{1}{Z(x)}\prod_{t=1}^{T}exp\{\sum_{k=1}^{K}\theta_kf_k(y_t,y_{t-...
0
votes
1answer
16 views

About discriminative/generative and directed/undirected graphical model?

I feel that most generative models happen to be DGM(directed graphical model), and most discriminative models are UGM(undirected graphical model). Is there any correlation between these concepts? ...
0
votes
0answers
20 views

Is there a branch of machine learning that can deal with near infinite state spaces

So I have a game type problem defined as follows; Up to 10 players Each player has: 64 tiles 200 piece types Up to 20 pieces in play at any time There's a random ...
0
votes
0answers
4 views

Determining an appropriate cost function given the type of problem and a hypothesis function

I'm studying up on machine learning basics and the standard high-level approach in supervised ML is to define a hypothesis function that maps inputs to outputs. Then define a "cost function" that ...
0
votes
0answers
7 views

prepare program code to dataframe for machine learning task [closed]

I am not sure, that i ask question in the right forum. If necessary, please suggest in which SO forum, I should write this question. I have free source with free program code of different categories (...
0
votes
1answer
7 views

Array of samples from multivariate gaussian distribution Python

I am trying to build in Python the scatter plot in part 2 of Elements of Statistical Learning. First it is said to generate 10 means mk from a bivariate Gaussian distribution N((1,0)T,I) and ...
4
votes
1answer
32 views

Top principal components versus most significant random forest variables

I was working on making a supervised learning model starting with a database of about 100 features and 1000 data entries. My goal is to predict a certain target variable. I tried three different ...
0
votes
0answers
5 views

Implementation of Traditional Language Models

Problem I am now reading this paper (A Bit of Progress in Language Modeling) to know language modeling techniques prior to methods based on neural network. However, since this paper is rather old (...
0
votes
1answer
13 views

Suggestion on Papers to Read on Classifier Selection

I'm looking for some papers to read to get started understanding classifier selection method in a computer security system. I wanted to develop a Multiple Classifier System based on a pool of ...
0
votes
1answer
19 views

Why Converting Regression to Ordinal Regression

Intro: Ordinal Regression/Classification is a classification where the labels have orders (https://en.wikipedia.org/wiki/Ordinal_regression) Question: Can you comment what are pros and cons if ...
0
votes
2answers
39 views

How to find out if there is any real pattern in the data set?

Let's assume that we have a regression problem (in the machine learning sense). Our data set consists of pairs of features vectors and numeric targets. It might be the case that there is absolutely ...
1
vote
1answer
44 views

Regression on Auction Prices, Multiple Prices Randomness

I'm currently building a model to predict internet auction sale prices of products in a marketplace. There are a lot of instances where a product goes for multiple prices but it's basically the same ...
1
vote
1answer
21 views

Should I use 5KFold or 10 KFold CV for data about 300000 sample?

I use logistics regression for binary classification. and my data is about 300 000 samples. I have used both kfold = 5 and kfold =10 cross-validation ...
0
votes
0answers
13 views

Hypothesis testing on two disproportionate samples

I want to conduct hypothesis testing on conversion rate of two disproportionate samples. One contains 20k Data points and other contains 180k datapoints. How can I do a hypothesis testing on such ...
2
votes
1answer
12 views

Model to Recommend Ideal Parameter Changes for Best Performance of Industrial Machine

I'm trying to develop a machine learning model to solve this problem, and am unsure of where to start. We begin with some user-defined settings. The settings are used by a machine to create a product....
1
vote
1answer
26 views

Regression when target has a wide range

I'm working on a regression model where I have to predict time. These times go from a few seconds to up to 30 min and more. I calculated the sMAPE through 1 minute bins of the target, and noticed ...
-1
votes
1answer
16 views

Kmeans Clustering with Hard Rules Included (in R) [closed]

I am beginning to work with kmeans clustering using the kmeans() function in R. I want to know, how is it possible to set up any hard rules for the clustering process? For instance, if the distance ...
0
votes
0answers
20 views

What type of neural networks should i use to learn model, which can generate music styles? [closed]

I have big dataset with different music styles(Techno, pop, rave, eurodance, trance, rock and classic in mp3 format from open resources) What type of neural networks should i use to learn model, ...
0
votes
1answer
20 views

How to use validation set in deep learning?

It is common to use a validation set to reduce overfitting for machine learning tasks. For traditional (non-neural network based) models, many validation techniques, such as cross-validation, can be ...
0
votes
0answers
11 views

Confidence vs. Count in association rule mining: which one is better?

I am writing a program that mines association rules from a large data set. I have an array of association rules, and I have to decide which ones are more representative of the patterns I am studying. ...
0
votes
0answers
7 views

How to infer results from tree-based feature selection and chi squared?

I have a data set with 12 continuous features, with 3 discrete output labels. I want to determine the two best features. My research thus far has led me to use chi^2 tests and extra tree classifiers ...
2
votes
0answers
26 views

What value to impute for informative NA values in R without misleading model

I'm building a model (random forest) in R to predict a rare event (scoring a goal in soccer). I have event-level data, which provides a log of all the actions (pass, tackle, foul, save, shot, goal) ...
0
votes
1answer
44 views

What is the role of k-fold cross validation?

When I search for the answer online, it seems like there is a disagreement on what cross-validation is. Some say k-fold cross validation is used to get an estimate of how well a model will perform ...
0
votes
0answers
15 views

The role of Fisher information matrix in Fisher kernel

I read the original paper proposed the Fisher kernel. The Fisher kernel is defined as $K(X_i,X_j) \propto U_{X_i}I^{-1}U_{X_j}$, where $U_X$ is the Fisher schore and $I$ is the Fisher information ...
2
votes
1answer
49 views

Why does differentiating the normalization term of a Binomial Distribution yield the expected value? [on hold]

In Bishop's book Pattern Recognition and Machine Learning, problem 2.4 aims to derive the expected value of the binomial distribution $m \sim Bin(N, \mu) = {N \choose m} \mu^m (1 - \mu)^{N-m}$ by ...
0
votes
0answers
13 views

Tree pruning & cost-complexity

This is a question in cost complexity pruning that I want to learn about. I am given $A ≥ 0$ to be the tuning parameter, where $t_0$ is the full tree, and $t$ is a subtree. We then have $|t|$ as ...
1
vote
1answer
19 views

Computing the trace of the sample covariance of projected data

Problem For a given dataset $\{x_1, \dots, x_n \}$ where $x_i \in \mathbb{R}^d$, assuming that we project each $x_i$ onto a unit vector $u$, and denote the projected data point as $\tilde{x}_i = (x_i^...
2
votes
1answer
63 views

Early stopping on validation set

There exist cases where one can "overfit" on the validation set. Although it is easier to overfit on the training set, the distributions of the validation and test set may not match, in which case ...
0
votes
0answers
13 views

Tree Pruning: SSE

Can someone show me an instance of a data set where a no split causes a reduction of SSE, however can be modeled by a tree with 3 splits? Basically, an example that shows that it's sometimes needed to ...
0
votes
0answers
3 views

Truncate a Hierarchical Clustering tree in order to get the cophenetic coefficient

I've gone ahead and clustered a dataset using a Euclidian Hierarchical Clustering algorithm: ...
0
votes
0answers
16 views

Infer statistical model prediction confidence coefficient based on the past predicted and actual results

Currently, I encountered such as a problem: For example, when I built a statistical model based on the past 3 month data and using the model to predict for the next month. But I found that the ...
0
votes
0answers
18 views

Accuracy of classification vs. accuracy of class probabilities

I have a dataset that contains a binary response variable: equal to 1 if the person responded to the survey and 0 otherwise, as well as a host of auxiliary variables X. What I want to do is use this ...
0
votes
1answer
38 views

High AUC but low R squared in a random forest classifier

I have been looking for an answer on this website and on Google but I can't seem to find a clear explanation anywhere. The problem is the following. I built a Random Forest model (using Python's ...
0
votes
0answers
8 views

how to check the distribution of the training set and testing set are similar

I have been playing the Kaggle Competition and I find there is a situation that the distribution of the training set and testing set are different, so I am wondering how to check the distribution of ...
0
votes
1answer
29 views

Chi Square Analysis Throws Error - The internally computed table of expected frequencies has a zero element at (0,)

I am trying to see the association between two variables. I used Chi-Square analysis in Scipy package in Python. Here is the crosstab result of the two variables: ...
3
votes
0answers
23 views

Can one use ridge regression to test hypotheses? [duplicate]

Are the parameters (the beta's) that result from a ridge regression interpretable as we normally do with canonical linear regression? Can I use them to test hypothesis? Or is ridge regression ...
0
votes
0answers
11 views

Grouping Similar Sequences

I have extracted a ton of log data from a mobile application. The objective of this task is to identify similar patterns of behavior. Which algorithm should I look at which will group behaviors ...
2
votes
0answers
16 views

Building a job recommendation system [closed]

I am building a job recommendation system where in i have the required skills for each role along with the value of the skill relevant for the role. Example of the dataset is as shown in the image. ...
1
vote
1answer
22 views

Optimising recall for multi-label classification?

I'm working on a multi-class multi-label classification problem where text (let's say comments on a website) should be assigned (possibly multiple) labels. There is a neutral (negative) class and ...
0
votes
0answers
13 views

Location-based time series: predicting Uber surge pricing

As a learning exercise, I'm working on putting together a few different machine learning projects that I can spend some time honing and studying. One of these projects is predicting the locations of ...
1
vote
0answers
10 views

Meaning of confidence factor in J48

I try to use J48 classifier from RWeka library in R (C4.5 algorithm). I can parametrize this classifier with C parameter which means 'confidence factor'. What does this value exactly mean? I know that ...
0
votes
0answers
13 views

RNN to predict completion of fixed-length time series

I need advice to model a certain kind of time series prediction for which I didn't find any existing solution. I have a large set of independent time series of fixed length (let's say 100 steps). All ...
2
votes
0answers
9 views

What are the important methods that evolved in computing optical flow?

I have gone through various approaches to find optical flow. But I have a tad confusion between Horn and Shunck method and Lucas Kannede method. Where are these methods useful and where do these ...
1
vote
0answers
50 views

Evaluating Unbalanced Multiclass Classifiers: Which Tests to Use? [closed]

I am looking for some comprehensive instructions and ideally out of the box solutions (ideally for python) for evaluating different classifiers (which are already trained) for a multiclass ...
0
votes
0answers
9 views

Are these Multi-label document classification experiment steps sensible?

I plan to filter an input document using 4 different labels. Just for an example, a document discussing about movie summary needs to be labeled with 4 labels (Romance, Drama, Fiction, Hollywood). ...
0
votes
0answers
5 views

Uncertainty quantification in both model and parameters of the model

In engineering analysis in my domain (civil engineering), we have many models based on partial differential equations. We predict the behavior of the system based on the parameters we measure from ...
0
votes
0answers
8 views

The Cochran and Cox Approximation Pair T test Unequal Variance

Hi everyone I hope you are well. Maybe as you know according to Behners-Fisher problem (unequal variance case of samples) there are some kind of approximations. I have recently covered the ...
0
votes
0answers
17 views

Getting Realistic Test Metric With Overlapping Train and Test Data

My question is a rather specific one, and I'll go into detail below, but basically boils down to this: Are there any ways to get realistic test accuracy for an SVM classifier fit on data that ...
0
votes
0answers
24 views

Bayesian Information Criterion Formula Proof

while I was digging arima model I saw that BIC value is given as $k*log(n)-2*log(L)$ where $L$ is the maximized value of likelihood function whereas $k$ is number of parameters. I wonder how it is ...