Machine Learning Types

Study Notes

Supervised Learning: The model is trained on labeled data, where the correct output is provided for each input. The goal is to learn a mapping between input and output.
Unsupervised Learning: The model is trained on unlabeled data, and the goal is to discover patterns or structure in the data.
Reinforcement Learning: The model learns by interacting with an environment and receiving feedback in the form of rewards or penalties.

Linear Regression: A linear model that predicts a continuous output variable.
Decision Trees: A tree-based model that splits data into subsets based on features.
Random Forest: An ensemble of decision trees that improves accuracy and reduces overfitting.
Support Vector Machines (SVMs): A model that finds the best hyperplane to separate classes.
Neural Networks: A model inspired by the human brain, composed of layers of interconnected nodes (neurons).

Overfitting: When a model is too complex and performs well on the training data but poorly on new, unseen data.
Underfitting: When a model is too simple and fails to capture the underlying patterns in the data.
Bias-Variance Tradeoff: The tradeoff between the error introduced by simplifying the model (bias) and the error introduced by fitting the noise in the data (variance).
Gradient Descent: An optimization algorithm used to minimize the loss function and find the optimal parameters.

Accuracy: The proportion of correctly classified instances.
Precision: The proportion of true positives among all positive predictions.
Recall: The proportion of true positives among all actual positive instances.
F1 Score: The harmonic mean of precision and recall.
Mean Squared Error (MSE): The average squared difference between predicted and actual values.

Image Classification: Classifying images into categories (e.g., objects, scenes, actions).
Natural Language Processing (NLP): Analyzing and generating human language (e.g., text classification, sentiment analysis, language translation).
Recommendation Systems: Suggesting personalized items or products based on user behavior and preferences.
Speech Recognition: Recognizing spoken words and phrases.

Supervised Learning: Training on labeled data to learn mapping between input and output.
Unsupervised Learning: Training on unlabeled data to discover patterns or structure.
Reinforcement Learning: Learning through interaction with environment, receiving feedback in rewards or penalties.

Linear Regression: Predicting continuous output variable using linear model.
Decision Trees: Splitting data into subsets based on features using tree-based model.
Random Forest: Improving accuracy and reducing overfitting using ensemble of decision trees.
Support Vector Machines (SVMs): Finding best hyperplane to separate classes.
Neural Networks: Modeling complex relationships using layers of interconnected nodes (neurons).

Overfitting: Model performs well on training data but poorly on new data due to complexity.
Underfitting: Model fails to capture underlying patterns due to simplicity.
Bias-Variance Tradeoff: Balancing error introduced by simplifying model (bias) and fitting noise in data (variance).
Gradient Descent: Optimizing loss function and finding optimal parameters using iterative algorithm.

Accuracy: Proportion of correctly classified instances.
Precision: Proportion of true positives among all positive predictions.
Recall: Proportion of true positives among all actual positive instances.
F1 Score: Harmonic mean of precision and recall.
Mean Squared Error (MSE): Average squared difference between predicted and actual values.

Image Classification: Classifying images into categories (e.g., objects, scenes, actions).
Natural Language Processing (NLP): Analyzing and generating human language (e.g., text classification, sentiment analysis, language translation).
Recommendation Systems: Suggesting personalized items or products based on user behavior and preferences.
Speech Recognition: Recognizing spoken words and phrases.