▎Common AI Terms

1. Artificial Intelligence (AI): The simulation of human intelligence processes by machines, particularly computer systems, encompassing learning, reasoning, and self-correction.

2. Machine Learning (ML): A subset of AI that focuses on the development of algorithms that allow computers to learn from and make predictions or decisions based on data.

3. Deep Learning: A specialized area of machine learning that uses neural networks with many layers (deep neural networks) to model complex patterns in large datasets.

4. Natural Language Processing (NLP): A field of AI that enables computers to understand, interpret, and generate human language in a meaningful way.

5. Computer Vision: A field of AI that enables machines to interpret and make decisions based on visual data from the world, such as images and videos.

6. Reinforcement Learning: A type of machine learning where an agent learns to make decisions by taking actions in an environment to maximize cumulative reward.

7. Supervised Learning: A machine learning approach where a model is trained on labeled data, meaning that the input data is paired with the correct output.

8. Unsupervised Learning: A machine learning approach where a model is trained on unlabeled data, allowing it to find patterns or groupings within the data without explicit guidance.

9. Semi-Supervised Learning: A hybrid approach that uses both labeled and unlabeled data for training, improving learning accuracy when labeled data is scarce.

10. Feature Engineering: The process of selecting, modifying, or creating features (input variables) from raw data to improve the performance of machine learning models.

11. Overfitting: A modeling error that occurs when a model learns the training data too well, capturing noise and outliers, which negatively impacts its performance on new data.

12. Underfitting: A situation where a model is too simple to capture the underlying trends in the data, resulting in poor performance on both training and test datasets.

13. Bias: Systematic errors in a model's predictions due to assumptions made during the learning process or due to biased training data.

14. Variance: The amount by which a model's predictions would change if it were trained on a different dataset; high variance can lead to overfitting.

15. Hyperparameter: Configurable parameters that are set before training a machine learning model (e.g., learning rate, batch size) and are not learned from the training data.

16. Confusion Matrix: A table used to evaluate the performance of a classification model by comparing predicted labels with actual labels, providing insight into true positives, false positives, true negatives, and false negatives.

17. Precision: A metric that measures the accuracy of positive predictions made by a classification model, calculated as the ratio of true positives to the sum of true positives and false positives.

18. Recall (Sensitivity): A metric that measures the ability of a classification model to identify all relevant instances, calculated as the ratio of true positives to the sum of true positives and false negatives.

19. F1 Score: The harmonic mean of precision and recall, providing a single score that balances both metrics, particularly useful in imbalanced datasets.

20. Transfer Learning: A technique where a pre-trained model is adapted for a new task, leveraging knowledge gained from one domain to improve performance in another.