An interview guide on common Machine Learning concepts, best practices, definitions, and theory.

Contents

1. Model Scoring Metrics
2. Parameter Sharing
3. k-Fold Cross Validation
4. Python Data Types
5. Improving Model Performance
6. Computer Vision Models
7. Attention and its Variants
8. Handling Class Imbalance
9. Computer Vision Glossary
10. Vanilla Backpropagation
11. Regularization
12. References

Model Scoring Metrics

• Classification Accuracy
• Log Loss
• Confusion Matrix
• Precision