Supervised learning
1. Decision tree: A decision tree is a decision support tool that uses a treemap or decision model and its possible consequences, including event outcomes, resource costs, and utility.
2. Naive Bayes classification: The Naive Bayes classifier is a series of simple probability classifiers based on the application of Bayes' theorem and the assumption of strong (naïve) independence between features. The feature image is the equation - P(A|B) is the posterior probability, P(B|A) is the likelihood, P(A) is the class prior probability, and P(B) is the predicted prior probability.
Examples of Bayesian classification are: · Mark email as spam or not spam; • Categorize news articles about technology, politics or sports; Check whether a piece of text expresses positive emotions or negative emotions? · Used in face recognition software.
3. Ordinary Least Squares Regression: Least squares is a method of performing linear regression. You can think of linear regression as the task of fitting a straight line through a set of points. There are several possible strategies to do this, the "ordinary least squares" strategy is like this - you can draw a line, and then for each data point, measure the vertical distance between the point and the line, and add them up; The fitted line will be the line where the sum of distances is as small as possible.
Linearity refers to the type of model used to fit the data, while least squares refers to the type of error measure to be minimized.
4. Logistic Regression: Logistic regression is a powerful statistical method that models binomial results with one or more explanatory variables. It measures the relationship between a categorical dependent variable and one or more independent variables by estimating probabilities using a logistic function, that is, a cumulative logistic distribution.
5. Support vector machine: SVM is a binary classification algorithm. Given a set of 2 types of points at an N-dimensional location, the SVM generates a (N-1) dimensional passing lane to divide these points into 2 groups. The SVM will find a straight line, divide these points into two types, and be as far away as possible from all of them.
6. Ensemble method: An ensemble method is a learning algorithm that constructs a set of classifiers and then classifies new data points by weighted voting on their predictions. The initial integration method was Bayesian averaging, but more recent algorithms include error correction output coding, bagging, and boosting.
Unsupervised learning
7. Clustering algorithm: Clustering is the task of grouping a group of objects so that objects in the same group (cluster) are more similar to each other than objects in other groups.
Clustering algorithm
8. Principal Component Analysis: PCA is a statistical process that uses orthogonal transformations to convert observations of a set of potentially correlated variables into values for a set of linear uncorrelated variables called principal components.
9. Singular value factorization: In linear algebra, SVD is a factorization of a complex matrix of real numbers. For a given m*n matrix M, there exists such a decomposition: M = UΣV, where you and V are unitary matrices and Σ is a diagonal matrix.
PCA is actually a simple application of SVD. In computer vision, the first face recognition algorithm uses PCA and SVD to represent faces as linear combinations of "feature faces", perform dimensionality reduction, and then match faces with identities through simple methods; Although modern methods are more sophisticated, many still rely on similar techniques.
10. Independent Component Analysis: ICA is a statistical technique used to reveal hidden factors behind random variables, measurements, or signal sets. ICA defines a generative model for the observed multidata, which is usually given in the form of a large sample database. In the model, it is assumed that the data variable is a linear mixture of some unknown latent variables, and that the hybrid system is also unknown. The latent variables are assumed to be non-Gaussian and independent of each other, and they are called independent components of the observational data.