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.

0
votes
0answers
3 views

Tools in Data Science

I am a new one in Data Science and Machine Learning. I have some experience in Java, Python, SQL, Jupyter and most polular libraries like scikit-learn, numpy, pandas, tensorflow, keras. What tools ...
0
votes
0answers
2 views

How to properly integrate data from multiple studies in a training/testing classification framework?

I currently have data from several studies, with each having different sample sizes and possibly different set-ups. There is a common binary variable of interest across all studies that I would like ...
0
votes
0answers
6 views

Eigenvalues as weighting factors for projection results on corresponding eigenvectors in PCA

In Novel PCA-based Color-to-gray Image Conversion, the authors "utilize the eigenvalues as weighting factors for projection results on corresponding eigenvectors", in order to project a $(R, G, B)$ ...
0
votes
0answers
5 views

How do I check my GAN implementation is correct?

I wrote a GAN implementation and I trained that to produce some sample images after training on a dataset. The images looked visually fine. Now I want to test my implementation on the CI and make ...
0
votes
0answers
12 views

GPU for fully-connected network?

I'm interested in neural networks from a general machine learning and pattern recognition perspective and not as much from the perspective of image processing or NLP data. If I want to train a neural ...
0
votes
0answers
14 views

Recommender system with extra variables

I would like to to create a recommendation engine that makes use of a utility matrix (user-item interactions) as well as supplementary features (user features, item features and time-based features). ...
0
votes
0answers
11 views

PCA/Higher dim-data

If we relate the eigenvectors $A = (1/N)Y^T Y$ and $B = (1/N)YY^T$, how can I show that there's a matching between the non-zero eigenspaces of the eigenvectors ($A$ and $B$), so that if $\lambda$ ...
0
votes
0answers
5 views

Modeling on entire dataset vs. Combining segmentation models trained on subsets of the same dataset

Training machine learning models on an unbalanced dataset: about 3% positive labels, and 97% negative. The modeling goal is to get as many examples as possible with 60% precision on a holdout test set ...
0
votes
0answers
8 views

Pretext Task in Computer Vision

I am new to Computer Vision. I am reading many papers and i see the term "pretext task". Can anyone explain what exactly it means. Thanks in Advance.
0
votes
0answers
11 views

What could cause CNN training accuracy to drop after 7th epoch

Question from DataScience - Which is the correct forum for this kind of question please? I am training a CNN on some new dataset. Usually, the accuracy steadily improves over 10-20 epochs. I have ...
0
votes
1answer
10 views

No need for bias term if data is standardised? Linear classification models

For linear classification models, e.g. perceptron, bias term allows to move separating hyperplane away from origin. If data is scattered around the zero does that mean that we don't need bias term?
0
votes
0answers
12 views

How to approach machine learning time specific data; which months of usage to use?

I am relatively new to the data science area and just have a question about how to approach a time specific machine learning problem. Just as an FYI I am currently using a random forest classifier for ...
2
votes
1answer
27 views

Statistically compare similarity between images

I have two images/heatmaps (2d matrix) of identical size. I need to statistically compare the similarity between the two. With 'similarity', I mean that high and low values of one image appear in ...
0
votes
1answer
7 views

How to choose the best number of installments to sell an item

I have a dataset about previous sales. It contains both sold and cancelled item information. Which includes prices and number of installements for the item. Here I want to increase the probability of ...
0
votes
0answers
14 views

Neural network models in time series forecasting

can we use NN models for non seasonal time series data like livestock population?
0
votes
0answers
5 views

Applying CRF to semantic segmentation

Confused on how to apply CRFs to semantic segmentation. I'm not able to find any good tutorials except this one. Is the process the following: First train a DNN on some training set. Generate ...
1
vote
0answers
10 views

Feature engineering for sheet music

I have a large dataset of digitized music scores that I'd like to use as input to a network. Initially, I'm looking to train networks to identify key signatures, tempo, dynamics, etc. from the raw ...
0
votes
1answer
25 views

What stops gradient descent from finding the largest error?

If a gradient points towards a max or a min what stops gradient descent from maximizing error instead of minimizing it? Is it the nature of the update step that makes this process one way?
0
votes
1answer
32 views

AUC of single model vs AUC of separate models on same data

I have created two separate binary classifiers that predict the same kind of label using 2 separate datasets. The data is in the same format. They both have a AUC of 0.94 and 0.95 I have then created ...
1
vote
0answers
39 views

Wrong fitted parameters in multivariate linear regression?

I am implementing multivariate linear regression using numpy, pandas and matplotlib. I then ...
1
vote
1answer
79 views

First Component in PCA

I was doing the Andrew Ng's ML course, and one of the solutions mentioned The first principal component is aligned with the direction of maximal variance. I didn't get what it is trying to say.
0
votes
0answers
13 views

What is the risk of not oversampling randomly?

Random Oversampling involves supplementing the training data with multiple copies of some of the minority classes.Instead of duplicating every sample in the minority class, some of them may be ...
5
votes
1answer
242 views

Statistical analysis applied to methods coming out of Machine Learning [on hold]

Most of the recent famous methods coming out of the machine learning, are supervised learning methods like Decision Trees, Random Forests, Deep Learning, SVMs. The more traditional supervised ...
0
votes
0answers
64 views

Box-Cox Transformation does not normalize data sufficiently sometimes [on hold]

initially as far as I have dug up on internet and books I have seen that Box-Cox transformation may not normalize data as we wish. Besides, log-likelihood function is maximised with $\lambda$ variable ...
1
vote
0answers
19 views

How can we call likelihood function a joint PDF when the individual terms do not represent Probabilty

My understanding of the Probabilty Density Function is that they evaluate to 0 at a particular point . So if we have some i.i.d points $x_{n}$ from a Normal distribution and we write : \begin{equation}...
-1
votes
0answers
29 views

why scikit-learn is so disgustingly overfitting? [on hold]

I bumped into a problem that dazzles me very much, I can't believe it's actually happening. I trained an elastic net using last version of scikit-learn function ElasticNetCV and a 4 folds CV repeated ...
0
votes
0answers
13 views

Coding Random Forrest in R [on hold]

I'm looking to code a random forest in R but am having a bit of trouble in my dataset. Before I get into the problem, let me reproduce my code below. The response variable of interest is '...
0
votes
0answers
23 views

Understanding backprop equations [on hold]

I was watching a video on backprop from deeplearning.ai where one particular thing confused me a lot. In the backprop, as shown below, Why aren't we averaging <...
0
votes
0answers
5 views

Approximate Bayesian Computation: Applications to Elevator Group Control Systems

I am working on a project where I will be using Approximate Bayesian Computation (Likelihood-Free Inference) in order to improve an Elevator Group Control System, e.g. minimize the waiting time of the ...
0
votes
0answers
18 views

How do you define the error in a hidden layer of a neural network? [on hold]

I am reading some introductory texts on neural networks. While I am able to understand that the error in the final layer of the neural network is but I am not able to understand how the errors in ...
1
vote
1answer
8 views

Having trouble figuring out how loss was calculated for SQuAD task in BERT paper

The BERT Paper https://arxiv.org/pdf/1810.04805.pdf Section 4.2 covers the SQuAD training. So from my understanding, there are two extra parameters trained, they are two vectors with the same ...
-1
votes
1answer
18 views

How to use convolutions of pictures instead of FC layers? [on hold]

How to use convolutions of pictures instead of FC layers? How can i do this effectively and efficiently.
0
votes
0answers
23 views

Logistic Regression - Coefficients not defined because of singularities

I am running a regression model to predict dropout from an online program. People have to take 5 classes but some people dropped before taking the 5 courses. So I am using a dummy variables that is 1 ...
0
votes
0answers
7 views

How to get top features that contribute to anomalies in Isolation forest

I am using Isolation forest for anomaly detection on multidimensional data. The algorithm is detecting anomalous records with good accuracy. Apart from detecting anomalous records I also need to find ...
0
votes
1answer
29 views

Changing the regression problem to a classification problem

I'd like to do the classification on a crime data around the country. However, what I have for the label is the crime coefficient which is from 0 to 1. I'd like to make up some interval like 0~0.3 as ...
3
votes
1answer
38 views

Are there any other image classification methods besides using neural networks?

When reading about image classification, the only occurring terms are "neural networks", "deep learning" and "CNN". It seems like there are no other methods for this task. I have worked with neural ...
0
votes
0answers
14 views

Deviance when y = 0

I am trying to compute deviance for the predictions of my dataset and I encounter quite a big problem here. Deviance is calculated as : $2 (\log(\mathrm{yTrue}) - \log(\mathrm{yPred}))$ where $\log$...
0
votes
0answers
10 views

Normalising predictions across datasets

I am currently training a model to predict a binary attribute. The model gives the output in range [0, 1]. The metric is TPR@FPR, e.g. I need to achieve maximum ...
2
votes
0answers
35 views

Bias Variance Decomposition 2.7 in Elements of Statistical Inference

I try to derive 2.7 from the book. I expose my demonstration $E_\tau[(y_0-\hat{y}_0)^2]=E_\tau[y_0^2]-2E_{\tau}[y_{0}\hat{y_{0}}]+E_{\tau}[\hat{y_{0}}^{2}]$ $= y_{...
0
votes
0answers
6 views

Why different seeds produce different mse values for regression tree and ols?

I compare regression tree and ols in terms of out of sample prediction. I realized that the mse values changed when i change the seeds before getting train and test set. Sometimes ols is better ...
0
votes
1answer
41 views

How do I implement stochastic gradient descent correctly?

I'm trying to implement stochastic gradient descent in MATLAB however I am not seeing any convergence. Mini-batch gradient descent worked as expected so I think that the cost function and gradient ...
3
votes
1answer
55 views

How to plot logistic decision boundary?

I am running logistic regression on a small dataset which looks like this: After implementing gradient descent and the cost function, I am getting a 100% accuracy in the prediction stage, However I ...
0
votes
0answers
13 views

XOR Neural Network, Problem finding shapes of delta for backpropagation algorithm

I am taking the Machine Learning course by Andrew Ng on coursera. I am trying to make a neural network learn to do XOR, but I am facing a problem regarding the shapes of the $\delta$ vectors, and $\...
0
votes
0answers
10 views

Best Machine Learning Algorithm for Grouping Similar Census/Survey [on hold]

I am working in a company which have many census/survey. The problem is there are so many census/survey that have similar questionnaire variable which made many of our census/survey seems to be ...
0
votes
0answers
14 views

Selecting SVM parameters if training data is oversampled/undersampled

I am working on classification for highly imbalanced data. Let's say I have a strategy to oversample/undersample the training data. I plan to use an SVM classifier to perform the classification. Now, ...
0
votes
0answers
18 views

Training error higher than test error and validation error

I am training a genetic algorithm for classification and strangely, the training error is consistently HIGHER than the validation and test error. The training and validation set are both small size ...
2
votes
1answer
54 views

Scaling data with different importance

I have 9 attributes: x1,x2,x3,x4,...,x9 and I know that the attributes x9 must have the same value in a cluster and the attribute X1 have more importance than others (x2,...,x8) I'm using Euclidean ...
0
votes
0answers
14 views

Encoding quantitative outputs for regression

From Elements of Statistical Learning: For a two-class G, one approach is to denote the binary coded target as Y , and then treat it as a quantitative output. The predictions Yˆ will typically ...
2
votes
2answers
34 views

How effective is SVM over big datasets?

I have a dataset of 800,000 observations and 11 features that I am using for a classification problem. I tried to optimize my model many times but in vain. The one thing I haven't tried is using SVM. ...
0
votes
0answers
17 views

is backpropagation appropriate for training actor-critic when using Neural networks? [on hold]

I'm confused whether the backpropagation is appropriate to train the actor as well as the critic. If it possible I would like to know what is the update part for both. I used already to rain the ...