Machine Learning Concepts Flashcards
Grade 11 · Technology · Flashcards
Core vocabulary for supervised learning, neural networks, unsupervised learning, and model evaluation.
Flashcards
- Machine Learning
- A branch of AI where systems learn patterns from data to improve performance without explicit programming.
- Supervised Learning
- Training on labeled input-output pairs to predict outputs for new inputs.
- Unsupervised Learning
- Finding hidden structure in unlabeled data through clustering or dimensionality reduction.
- Feature
- An individual measurable input variable used by a model (e.g., height, pixel value, word count).
- Label
- The known correct output for a training example in supervised learning.
- Training Set
- The portion of data used to fit model parameters.
- Test Set
- Held-out data used to evaluate final model performance; must not influence training.
- Overfitting
- Model too closely fits training data, generalizes poorly to new examples.
- Regularization
- Techniques (L1, L2, dropout) that penalize model complexity to reduce overfitting.
- Gradient Descent
- Iterative optimizer adjusting parameters by moving opposite the gradient of the loss function.
- Neural Network
- Layered architecture of weighted nodes + activation functions learning hierarchical representations.
- K-Means
- Partitions data into k clusters by minimizing average squared distance to each cluster center.
- Precision
- True positives / (True positives + False positives) — accuracy of positive predictions.
- Recall
- True positives / (True positives + False negatives) — coverage of actual positives.
- F1-Score
- Harmonic mean of precision and recall; balances both metrics into a single score.
Get a personalized course on Machine Learning Concepts built around your child.