Across
- 2. A model architecture primarily used in NLP that understands context in sequences (e.g., ChatGPT is built on one).
- 4. The capacity of an AI to act independently or make choices.
- 6. Vision, AI’s ability to interpret and process visual information from the world.
- 8. The ability to understand and explain how an AI system makes decisions.
- 12. Configuration settings used to control the learning process in machine learning models.
- 13. A set of rules or instructions given to an AI system to help it learn or solve problems.
- 16. Adversarial Networks, Two neural networks competing against each other to improve the quality of generated data.
- 18. A training technique for neural networks where the model adjusts weights to reduce error.
- 19. Simplified rules or strategies used to solve complex problems efficiently.
Down
- 1. Learning, A type of learning where an agent learns to make decisions by receiving rewards or penalties.
- 3. A hypothetical point when AI surpasses human intelligence, possibly leading to unpredictable outcomes.
- 5. Techniques to prevent overfitting in models.
- 7. When a model produces unfair results due to prejudiced training data.
- 9. When a model learns training data too well, including noise, and performs poorly on new data.
- 10. Network, A series of algorithms that mimic the way the human brain processes data.
- 11. Language Processing, The field of AI that focuses on the interaction between computers and human language.
- 14. Learning, Reusing a pre-trained model on a new, related task.
- 15. Descent, An optimization method used to minimize the error in AI models.
- 17. Moral considerations around how AI is used and its societal impacts.