Please enable JavaScript.

Coggle requires JavaScript to display documents.

Machine learning - Coggle Diagram

- - - - The Output is continuous
      - We can use it to find relation between Dependent variable and independent variable.
    - - I-Linear regression
        
        Multiple linear
        
        Polynomial
      - II-Decision tree
        
        The more nodes it has, the more accuarate the output will be.
      - III-Random forest
        
        1-Esemble learning tchnique that builts off over decision trees
        
        2-Involve creating multiple decision trees using bootstrap data sets of original data and randomly selecting a subset of variables at each step of the decision tree
        
        3-The model then selects de mode of all the predictions of each decision trees and by relying on the "majority wins" model, it reduces the risk of error from individual tree.
      - IV-Neural network
        
        Color interpretention
        
        Blue: input layer.
        
        Black: hidden layer
        
        Each node represents a function that input goes through ultimately leading to the output.
        
        Green: Output layer.
  - - - I-Logistic regression
        
        Used to model de probability of a finite number of outputs: 0 and 1 (outputs values)
      - II-Support Vector machine
        
        It is a supervised classification technique that carries an objective to find a hyperplane in n-dimensional space that cans distinctly classify the data points.
      - III-Naive Bayes
        
        It's a clasifier that acts as a probabilistic machine learning model used for classification tasks
        
        The crux of the classifier is based on the Bayes theorem.
      - IV-Decision tree; Random Forest; Neural network (but with discrete output)
- - - - Grouping of data points
      - Frequently used for customer segmentation fraud detection and document classification.
      - Techniques: K-means; Hierarchical; Mean shift; Density based
    - - Process of reducing dimensions of your feature set.
      - Techniques: feature elimination; feature extraction
      - Popular method: Principal Component Analysis (PCA)