Across
- 1. Behaviors or abilities that weren't explicitly programmed but arise from complex systems
- 5. The essential input that machine learning models need to learn patterns and make predictions
- 6. The IBM supercomputer that defeated chess champion Garry Kasparov in 1997, a landmark moment in AI history
- 9. These are AI systems trained on vast amounts of text data to understand and generate human language
- 10. A Specific objective or "_ _ _" to achieve through reward optimization
- 11. An optimization algorithm used in machine learning to adjust model weights based on how frequently parameters get updated
- 13. A type of machine learning where models learn from labeled examples
- 14. Connected computers form this
Down
- 2. The basic computational unit in a neural network, analogous to neurons in a brain
- 3. When AI generates information that seems plausible but is factually incorrect or made up. This is a significant challenge in current AI systems.
- 4. Computing systems inspired by biological brains
- 7. The instructions or queries given to an AI system
- 8. A learning approach where models identify patterns in data without labeled examples, discovering structure on their own
- 12. The simulation of human intelligence in machines programmed to think and learn