| Training Data |
The dataset used to teach the model patterns and relationships. |
| Validation Data |
Data used to tune model parameters during training and prevent overfitting. |
| Test Data |
Unseen data used to evaluate the final model performance. |
| Overfitting |
When a model performs well on training data but poorly on new, unseen data. |
| Underfitting |
When a model is too simple to capture patterns in the data. |
| Supervised Learning |
Training a model on labeled data (input-output pairs). |
| Unsupervised Learning |
Training a model to find structure in unlabeled data (e.g., clustering). |
| Semi-supervised Learning |
Learning using a small amount of labeled data and a large amount of unlabeled data. |
| Reinforcement Learning |
Training an agent to make decisions by rewarding desired behaviors. |
| Epoch |
One complete pass through the entire training dataset. |
| Batch Size |
The number of training examples used in one iteration of model training. |
| Learning Rate |
How much the model’s parameters are updated during training. |
