Basic Definitions
Updated
•2 min read| Concept | Definition / Description | Important Facts / History |
| Machine Learning (ML) | A field of study that gives computers the capability to learn without being explicitly programmed. ML is considered a subfield of artificial intelligence (AI). | The term Machine Learning was first coined by Arthur Samuel in 1959. The primary goal is to understand the structure of data and fit that data into models that people can utilize. |
| Algorithm | A set of rules and statistical techniques used to learn patterns from data and extract significant information from it. It provides the underlying logic behind a Machine Learning model. | The Linear Regression algorithm is provided as an example of an ML algorithm. |
| Model | The main component of Machine Learning. It is trained using an ML algorithm and is designed to map all decisions based on the given input to achieve the correct output. | — |
| Hypothesis | An assumption made by scientists, or a proposed explanation based on assumptions,. The model serves as a mathematical representation used to test the hypothesis. | In ML, the primary aim is to determine the possible hypothesis that best maps the input to corresponding outputs. The terms "Hypothesis" and "Model" are sometimes used interchangeably. A good hypothesis is testable, resulting in conclusions that are either true or false,. |
| Generalization | The ability of a trained machine learning model to classify or forecast unseen data. | To train a generalized model, factors like the dataset (diversity), the ML algorithm, model complexity, and regularization must be considered,. |
| Training Data | The data used to build the Machine Learning model, which helps the model identify key trends and patterns essential for predicting the output. | — |
| Testing Data | The dataset used, after training the model, to evaluate how accurately the model can predict an outcome. | — |
| Predictor Variable | A feature or features of the data that are used to predict the output. | Also known as the independent variable (like 'x' in linear regression). |
| Response Variable | The feature or output variable that needs to be predicted using the predictor variable(s). | Also known as the output or dependent variable (like 'y' in linear regression),. |
19 views