Different Types Of Machine Learning

1. Supervised Learning

• Supervised Learning is a type of Machine Learning where the model is trained using labeled data.

• Both input features (X) and target output (Y) are known.

• The goal is to learn a mapping from inputs to outputs and make accurate predictions.

1.1 Regression

• Regression is a supervised learning technique used to predict continuous numerical values.

• The output variable is a real-valued number.

• 1.1.1 Linear Regression

  • Predicts output using a straight-line relationship between variables.

• 1.1.2 Polynomial Regression

  • Models non-linear relationships by using polynomial terms.

• 1.1.3 Multiple Linear Regression

  • Uses multiple independent variables to predict a single output.

• 1.1.4 Decision Tree Regressor

  • Uses a tree structure to predict continuous values.

• 1.1.5 Random Forest Regressor

  • An ensemble of decision trees used to improve prediction accuracy.

1.2 Classification

• Classification is a supervised learning technique used to predict categorical outcomes.

• The output variable belongs to a fixed set of classes.

• 1.2.1 Logistic Regression

  • Predicts probabilities and is mainly used for binary classification.

• 1.2.2 Decision Tree Classifier

  • Uses decision rules to classify data into categories.

• 1.2.3 Random Forest Classifier

  • Uses multiple decision trees to improve classification accuracy.

• 1.2.4 Support Vector Machine (SVM)

  • Finds the optimal boundary to separate different classes.

• 1.2.5 K-Nearest Neighbors (KNN)

  • Classifies data based on the majority class of nearest neighbors.

• 1.2.6 Naive Bayes

  • A probabilistic classifier based on Bayes’ Theorem.

---

2. Unsupervised Learning

• Unsupervised Learning is a type of Machine Learning where the data is unlabeled.

• The model discovers patterns and structures in data without predefined outputs.

2.1 Clustering

• Clustering groups similar data points together based on their features.

• No target variable is used.

• 2.1.1 K-Means Clustering

  • Divides data into K clusters based on distance.

• 2.1.2 Hierarchical Clustering

  • Builds clusters in a hierarchical tree structure.

• 2.1.3 DBSCAN

  • Forms clusters based on density and identifies outliers.

2.2 Dimensionality Reduction

• Dimensionality Reduction reduces the number of input features while retaining important information.

• It helps improve model performance and visualization.

• 2.2.1 Principal Component Analysis (PCA)

  • Transforms data into fewer dimensions by maximizing variance.

• 2.2.2 Linear Discriminant Analysis (LDA)

  • Reduces dimensions while maximizing class separability.

---

3. Semi-Supervised Learning

• Semi-Supervised Learning uses a small amount of labeled data along with a large amount of unlabeled data.

• It is useful when labeling data is expensive or time-consuming.

3.1 Learning Methods

• 3.1.1 Self-Training

  • Model trains itself using its own predictions as labels.

• 3.1.2 Co-Training

  • Uses multiple models to label unlabeled data.

• 3.1.3 Graph-Based Learning

  • Uses graph structures to propagate labels.

---

4. Reinforcement Learning

• Reinforcement Learning is a learning method based on trial and error.

• An agent learns by interacting with an environment and receiving rewards or penalties.

4.1 Value-Based Methods

• Value-Based methods learn the value of actions to maximize rewards.

• 4.1.1 Q-Learning

  • Learns an optimal action-selection policy using a Q-table.

• 4.1.2 Deep Q Networks (DQN)

  • Uses neural networks to approximate Q-values.

4.2 Policy-Based Methods

• Policy-Based methods learn a direct mapping from states to actions.

• 4.2.1 Policy Gradient

  • Optimizes the policy directly using gradients.

• 4.2.2 Actor-Critic

  • Combines value-based and policy-based approaches.

---

Difference Between Algorithms

Type of Learning	Data Type	Main Tasks	Examples
Supervised Learning	Labeled data	Classification, Regression	Spam detection, Price prediction
Unsupervised Learning	Unlabeled data	Clustering, Dimensionality Reduction	Customer segmentation, Anomaly detection
Reinforcement Learning	Interactive (Environment feedback)	Sequential decision-making, Control	Game AI, Autonomous driving
Semi-supervised Learning	Small labeled + large unlabeled data	Classification, Clustering	Image recognition with few labeled samples
Self-supervised Learning	Unlabeled data (auto-generated labels)	Representation learning, Pre-training	Models like BERT, GPT (pre-training stage)