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.

Filter by
Sorted by
Tagged with
0
votes
1answer
11 views

Custom metrics for multiclass classification when class errors have different weights

I have a multiclass classification problem (eg. the target variable is made by 4 different outcomes: Product A, Product B, Product C and NO Product). Not all the errors are equal: for example, if the ...
1
vote
0answers
13 views

Optimizing hyperparameters of network with extremely long training time

As an example, let's say i am using a very deep fully convolutional autoencoder to segment lung scans. Input image resolutions will be large, since the features i hope to segment (things like early ...
2
votes
1answer
14 views

Precision-Recall representation - last value of the curve

When reading of precision-recall curves and seeing examples, the last point of the curve is always a given value of precision for a recall of 1. I'm a little confused about this. I have a detector ...
0
votes
1answer
16 views

Why is an ROC curve TPR (Y) against FPR (X)?

I am trying to thoroughly understand the ROC Curve and I was wondering why is an ROC Curve always (seemingly) TPR against FPR? I have had discussions with others about this matter and I cannot think ...
1
vote
0answers
10 views

What is the difference between an autoassociative neural network and an autoencoder?

I am looking at the use of autoencoder for dimensionality reduction, and so far I have been under the impression that autoassociative neural network = autoencoder, is that the case? and if not what ...
0
votes
1answer
16 views

What is the difference between multi-class and multi-label classification? [duplicate]

What is the exact difference between multi-class and multi-label classification? For example, if you have a fridge with a camera that can view inside to see what products are still in stock, is this ...
0
votes
0answers
10 views

Diversity enhancing sampling from positively dependent random measures

Is there any efficient method to maximize diversity of samples when sampling from a set of positively dependent random variables?
0
votes
1answer
27 views

is there a threshold to using deep learning rather than classical machine learning?

I was wondering when I should decide on using deep learning rather than using classical ML algorithms such as SVM or decision trees etc. Is there any threshold or rule of thumb in terms of the number ...
0
votes
0answers
7 views

Creating ANN's for multiple related datasets

I have three datasets, each representing time-series water quality data from three different regions (upper, middle, lower regions) of the same geographic area. I want to create different types of ...
1
vote
1answer
34 views

Expected Counts in Chi-Squared Goodness-of-Fit Tests of Normality

I have a variable with of 200 values that I would like to test for normality using the Chi-square Goodness of Fit test. To do this, I have to calculate, for each value, the expected value in a normal ...
0
votes
1answer
19 views

Creation of a Target Variable

So i'm new to machine learning and data science, i've been looking tutorials and i'm working on self made project at the moment and i'm having an analysis paralysis with the data preprocessing portion....
0
votes
0answers
13 views

Using certain percent of weights from certain featurs in machine learning model

I am trying to build a ML model which should predict the winner,2nd place and 3rd. The dataset has 15 features. However I want to have 80% influence of 9 features and the 20% from the rest of the ...
0
votes
1answer
13 views

Machine Learning models and “rare-event” independent variables

I have a data set which tries to predict a continuous variable, say house prices $Y$. My independent variables consits of things such as, square meters, number of bedrooms, bathrooms etc. However, I ...
0
votes
0answers
8 views

What is a good accuracy for Naive Bayes Classifier?

I'm currently train the Naive Bayes Classifier in TextBlob for my Sentiment Analysis. Before I used the training I had many positive or negative sentences that were determined as neutral sentences, so ...
0
votes
0answers
7 views

Priority between feature engineering and normalisation

My question is related to the priority between feature engineering (for example a simple transformation) and normalisation. It is a general question and I am not sure I understand all the ...
0
votes
0answers
21 views

Doubt about the formula for “The on-policy distribution in episodic tasks”

I've read the post how Deriving the formula for "The on-policy distribution in episodic tasks"? but I've a problem. If I apply the sum for all states $s \in \mathcal {S}$ in $$ \eta(s) = h(...
0
votes
0answers
15 views

N-Dimensional p-Wasserstein distance in Python [closed]

I need to compute the the p-Wasserstein distance between two n-dimensional empirical distributions in Python. Even though there are 1-d implementations, I still cannot find anything that solves the n-...
0
votes
0answers
16 views

How can we use Kolmogorov-Smirnov Test in ML?

I read about Kolmogorov-Smirnov Test. I understand that we can use Kolmogorov-Smirnov in 2 ways: Test if samples follows a given distribution Test if 2 variable (samples) have identical ...
0
votes
0answers
17 views

Gradient Boosting and neural networks

Is there any Python package that implements a boosted neural network ? Any pointer is appreciated. A sample reference about the boosting and NN can be this one.
0
votes
0answers
5 views

Gaussian Process Regression for High Dimensional Data: Vanishing predicted y values

I am working on a dataset with roughly 196 dimensions. I have been trying to fit Gaussian Process Regression into this dataset but it does not perform well. Mathematically speaking, I found out that ...
1
vote
0answers
8 views

How to train a meta-learning model?

In meta-learning we are suppose to train task ($\mathcal{T}_{i}$) with meta-train dataset ($\mathcal{D}_i^{\text{tr}}$). Say, we are training a 5-way ($N:5$) 2-shots $K:2$ meta-learning model with ...
2
votes
0answers
18 views

Why perform cross-validation to select best number of principal components when doing PCA, and then repeat PCA on a single train test split?

I'm currently looking through Chapter 6 of An Introduction to Statistical Leanring by Gareth James. I am working through the Chapter 6 lab regarding Principal Component Analysis. In the lab we first ...
2
votes
2answers
35 views

Does accuracy increase linearly when you add more factors/features to a random forest?

I have read in various machine learning books that adding more data should result in a more accurate model. Is this rule the same for adding more factors/features to the model as well? So, should I ...
0
votes
0answers
14 views

Daily timeseries decomposition into seasonal, trend, remainder?

I have time series for each day, that captures the time(s) of the day where a certain event $E$ happens (or alternatively, when it certainly isn't happening). This looks like the following: ...
0
votes
1answer
21 views

Imbalanced data for multiclass classification with ConvNet

I am trying to apply the SMOTE sampling technique to over-sample the minority class of a multiclass (5-class) problem using the convolutional neural network. As far CNN requirement, the input shape ...
3
votes
0answers
25 views

Why are the Polynomial Features used in a Linear Regression model not working as expected as the degree increases?

I'm fitting several polynomial regression models of varying degree. The smaller degree models (1 to 7) are behaving as expected. However, as the model increases in degree (8 or higher), the fitted ...
0
votes
0answers
14 views

How to approach Feature Extraction and Feature Selection part in machone learning in python?

I am a bit new to machine learning and I have the following questions: Question 1: When dealing with feature extraction with signals from sensors, what is the typical approach to extract features ...
1
vote
0answers
15 views

How to study Maths for ML [closed]

I have started Machine Learning but I am not sure up to what extent should I study its Maths part and also from where to study it. I am more interested in Machine Learning's application part building ...
1
vote
0answers
9 views

Best way for robust hand tracking on PI 4

I need a robust hand tracking which should be running on a Raspberry Pi 4 model. Does anyone have some experience with that? One way could be to use OpenCV but I think it's just using the skin color ...
7
votes
3answers
924 views

What happens in the sub-areas of AI? (ML, DL)

I have problems with understanding the sub-areas of AI and how it works. AI has the sub-area Machine Learning (ML), in which learning algorithms are used. Supervised/unsupervised learning takes place ...
1
vote
1answer
20 views

categorical distribution in validation set

I have a dataset that contains 6877 samples. This is a multiclass multilabel classification which means that we have 9 classes and every sample can belong to one or more of these classes. The total ...
1
vote
1answer
20 views

How to adapt the equations for stochastic gradient descent for batch gradient descent for neural networks?

I’m following along this lecture on neural networks. The professor derives equations for the gradient of $e(w)$: $\frac{\partial e(w)}{w_{ij}^l}$ for every $w_{ij}^l$ where $e(w)=e(h(x_n),y_n)$ is the ...
2
votes
1answer
35 views

How can you do regression when two groups of variables sum to each other?

Suppose I have a model like this: $$ y = \beta_1x_1 + \beta_2x_2 + \beta_3z_1 +\beta_4z_2 + \epsilon $$ where $\epsilon$ is noise. It so happens that $$x_1 + x_2 = z_1 + z_2$$ but there is no ...
0
votes
0answers
10 views

Disadvantages of the Point-wise Approach in Learning to Rank

I'm studying approaches to learning-to-rank for Information Retrieval and I'm having trouble understanding one of the commonly listed disadvantage to using point-wise solutions like binary ...
0
votes
0answers
11 views

What is “proxy datasets”? [closed]

People use the term "proxy datasets" a lot, I googled it, went through several papers but still don't understand the concept. Could someone please give a hint? Thanks in advance.
0
votes
0answers
16 views

Is there problem with low epoch, high accuracy?

I am training a complex neural network model and it starts to overfit epoch 3-4 so I stopped training at that level. So I don't think that there is any wrong thing ...
0
votes
0answers
24 views

Why is my Neural Network not learing?

I am interested in building a classifier for what time of the day a certain event happens. In my dataset I have two classes in feature "state", True or False, the $sin(x)$ and $cos(x)$ transform of ...
1
vote
0answers
7 views

Gaussian mixture models for image matrix not determining E step

I want to calculate responsibility for each of the data points, for the given MU, SIGMA and PI. ...
1
vote
2answers
24 views

Why is MSE used in cross validation when selecting optimum number of variables in model?

I'm currently looking through An Introduction to Statistical Learning by Gareth James, more specfically Chapter 6. It discusses ways to select the optimal number of variables in a model using methods ...
0
votes
0answers
18 views

Understanding notation in Bias-Variance decomposition in Elements of Statistical Learning

I'm going through Elements of Statistical Learning and I'm having a bit of trouble understanding this bit of notation from Chapter 2 (this example is (2.27)) $$EPE(x_0) = E_{y_o|x_o}E_T(y_0 - \hat{y}...
1
vote
2answers
18 views

Should I normalize all data prior feeding the tensorflow models?

Appreciate your wisdom on this, My understanding is most of the tutorials recommend normalizing / scaling the data prior feeding the tensorflow models. Doesn't normalization require that data ...
1
vote
1answer
15 views

Is Matrix Factorization also going to work with one feature?

I need to fill missing values. I have found that there are many approaches such as the mean and the median of the feature as well as using Matrix Factorization. However, I am kind of wondering if I ...
0
votes
0answers
25 views

Batch normalization leads to unstable validation loss

I'm working on a regression problem, and I'm trying to solve it using a simple multilayer perceptron with batch normalization. However, there are uncomfortably large fluctuations in the validation ...
1
vote
0answers
7 views

Mahalanobis distance between high dimensional arrays

As we know, the Mahalanobis distance (MD) is one of the distance metrics for measuring two points in multivariate space. In practice, I can compute Mahalanobis distance between two 1D arrays using ...
0
votes
0answers
20 views

what is “Nearest Neighbor Analysis”

I understand the explanation of "Nearest Neighbor Analysis" in a post. I also understand the kNN algorithm. However, a research paper call this "Nearest Neighbor Analysis". Without giving any ...
1
vote
1answer
21 views

Is Gaussian process model impacted by order of variable index?

I'm learning about Gaussian Process through this video by Richard Turner (University of Cambridge, link below). In the video, it was explained that GP is a generalization of multivariate Gaussian ...
1
vote
1answer
24 views

Time Series Analysis and Forecasting of Astronomical data having a sinusoidal trend

I have data of an orbital parameter of a satellite for 456 days. I am treating this data as univariate time series data and wish to use time series models to forecast future values. However, this data ...
1
vote
1answer
19 views

Does it make sense to calculate cross validation test error for a logistic model that has been ridge regressed?

I am working with the famous white wine dataset, and I am trying to fit a logistic model on it, where I also perform ridge regression on this logistic model. Finally, I want to calculate the test ...
0
votes
0answers
35 views

Find corresponding elements in two matrices with many-to-many relationships

I have to matrices, one is the matrix of diagnoses, the other is the matrix of tests. Some tests are always done, some are done to confirm several and some for very few cases. I would like to learn ...
0
votes
0answers
16 views

Is this Keras LSTM model underfitting? [closed]

I think this model is underfitting. Is this correct? ...

1
2 3 4 5
291