2

Variance in a feature (defined as the average of the squared differences from the mean) is important in machine learning because variance impacts the capacity of the model to use that feature. For example, if a feature has no variance (e.g., is not a random variable), the feature has no ability to contribute to task performance. A zero variance feature will ...


2

K-means don't modify the underlying structure of your data. K-means will just provide the 'color' part of your graph. To answer the question about why do you get a cuboid, it's because your underlying data are a cuboid. Not necessarily by construction, but that's what happen when you cap your data. As an exemple, look at the following code : X1 = c(rnorm(...


2

Without labels for which data points are anomalies, you have no way to know how many anomalies you should get. The closest thing to adding anomalies to the dataset is using synthetic data for anomaly detection. I have seen some practitioners doing this, and failing. When you create the synthetic data, it matches your inductive bias*. The real world very ...


1

Empty cells can be considered NaN of missing values. There are several ways to work with missing values. You can check this source: Encode NAs as -1 or -9999. This works reasonably well for numerical features that are predominantly positive in value, and for tree-based models in general. This used to be a more common method in the past when the out-of-the ...


1

welcome to the community. There are many criteria on the basis of which you can cluster the recipes. The usual way to do this is to represent recipes in terms of vectors, so each of your 91 recipes can be represented by vectors of 40 dimensions. This means that now the system or machine will identify your recipes as vectors in a 40-dimensional space. Now, ...


1

Recommendation Systems In recommendation systems the idea of extracting signal and using to make recommendations is very common, e.g, Alternating Least Squares and Singular Value Decomposition approaches. Autoencoder fits quite well, reducing dimensionality (the encoder part) should help extract signal. The weights in the network represent the behavior of ...


1

I did something similar a while ago. We wanted to classify several types of pdf. We first extracted the text of the documents. We created NLP features with the text Then added pdf metadata: size of the file, number of pages, name of the document... We then built a classification model with a few samples and did Active Learning I guess that you could also ...


1

Autoencoders are used to reduce the dimensionality of the feature space. They can capture nonlinearities that other dimensionality reduction teqniques like PCA can not. Autoencoders are build by training the model to reproduce the input. In this case you can split the data set into three: training cross validation testing Train you model using the training ...


Only top voted, non community-wiki answers of a minimum length are eligible