Notes – Key ML Terminologies
Understanding the basic terms in Machine Learning is essential before building models or analyzing data. These core concepts form the foundation of all ML techniques.
1. Dataset
A dataset is a collection of data, often in rows and columns.
- Each row = one observation or example
- Each column = a feature or variable
Example: A dataset of house prices with columns like area, location, and price.
2. Features (Independent Variables)
Features are the input variables used to make predictions.
Example: In a model predicting salary, features could be age, education, and experience.
3. Label (Target / Dependent Variable)
The output or result that the model is trying to predict.
Example: In a loan approval model, the label could be “Approved” or “Rejected”.
4. Model
An ML model is a mathematical representation that learns the relationship between features and labels from data.
Example: A Linear Regression model that predicts house price from size.
5. Training
The process where a model learns from the training data — it adjusts itself to minimize errors.
6. Testing
The phase where the model is evaluated on unseen data to check how well it performs.
7. Overfitting
When the model performs well on training data but fails on new data — it has “memorized” the training data instead of learning patterns.
8. Underfitting
When the model is too simple and fails to capture the pattern in data — it performs poorly on both training and test data.
9. Supervised Learning
ML method where the model learns from labeled data.
Example: Predicting marks from hours studied.
10. Unsupervised Learning
ML method where the model finds patterns in unlabeled data.
Example: Grouping customers based on buying habits.
