Read on Twitter
Day 7: Machine Learning Models (Intro)
In this short thread, we will look at the Machine Learning Model.
What is ML Model?
Machine learning model is the Output of the training process and is defined as the mathematical representation of the real-world process. https://twitter.com/RealSaintSteven/status/1290414402236305408
In this short thread, we will look at the Machine Learning Model.
What is ML Model?
Machine learning model is the Output of the training process and is defined as the mathematical representation of the real-world process. https://twitter.com/RealSaintSteven/status/1290414402236305408
*Types of Machine Learning Models
Based on the type of tasks we can classify machine learning models in the following types:
1. Classification Models
2. Regression Models
3. Clustering
4. Dimensionality Reduction etc
#ML #AI #Data #MachineLearning
Based on the type of tasks we can classify machine learning models in the following types:
1. Classification Models
2. Regression Models
3. Clustering
4. Dimensionality Reduction etc
#ML #AI #Data #MachineLearning
1 Classification: is the task of predicting the type or class of an object within a finite number of options.
The output variable for classification is always a categorical variable.
Let’s look at some important models for classification problems:
The output variable for classification is always a categorical variable.
Let’s look at some important models for classification problems:
a. K-Nearest neighbours algorithm
b. Naive Bayes: Bayes theorem.
c. Logistic Regression: Linear model for binary classification.
d. SVM: it can be used for binary/multiclass classifications.
e. Decision Tree: ‘If Else’ based classifier, more robust to outliers.
b. Naive Bayes: Bayes theorem.
c. Logistic Regression: Linear model for binary classification.
d. SVM: it can be used for binary/multiclass classifications.
e. Decision Tree: ‘If Else’ based classifier, more robust to outliers.
2. Regression
In ML regression is a set of problems where the output variable can take continuous values. e.g, predicting the price of Garri can be considered as a standard regression task.
Let’s look at some important regression models used in practice.
In ML regression is a set of problems where the output variable can take continuous values. e.g, predicting the price of Garri can be considered as a standard regression task.
Let’s look at some important regression models used in practice.
*Linear Regression: simplest baseline model for regression task
*Lasso Regression: Linear regression with L2 regularization.
*Ridge Regression: Linear regression with L1 regularization.
*SVM regression
*Decision Tree Regression etc.
*Lasso Regression: Linear regression with L2 regularization.
*Ridge Regression: Linear regression with L1 regularization.
*SVM regression
*Decision Tree Regression etc.
3. Clustering
Clustering is the task of grouping similar objects together. It helps to identify similar objects automatically without manual intervention.
Clustering helps us achieve this in a smarter way.
Some of the widely used clustering models:
Clustering is the task of grouping similar objects together. It helps to identify similar objects automatically without manual intervention.
Clustering helps us achieve this in a smarter way.
Some of the widely used clustering models:
*K means: Simple but suffers from high variance.
*K means++: Modified version of K means.
*DBSCAN: Density-based clustering algorithm etc.
*Agglomerative clustering: A hierarchical clustering model.
*K means++: Modified version of K means.
*DBSCAN: Density-based clustering algorithm etc.
*Agglomerative clustering: A hierarchical clustering model.
3. Dimensionality Reduction
Dimensionality is the number of predictor variables used to predict the independent variable or target.often in the real world datasets the number of variables is too high.
Too many variables also bring the curse of overfitting to the models.
Dimensionality is the number of predictor variables used to predict the independent variable or target.often in the real world datasets the number of variables is too high.
Too many variables also bring the curse of overfitting to the models.
*PCA: It creates lesser numbers of new variables out of a large number of predictors. The new variables are independent of each other but less interpretable.
*SVD: Singular value decomposition is used to decompose the matrix into smaller parts in order to efficient calculation.
*SVD: Singular value decomposition is used to decompose the matrix into smaller parts in order to efficient calculation.
In this thread, we look at important machine learning models used for practical purposes. Choosing a proper model for a particular use case is very important to obtain the proper result of a machine learning task.
