Across
- 3. (strong AI) - AI that can adapt and implement knowledge in a wide variety of tasks.
- 4. A type of neural network architecture that transforms or changes an input sequence into an output sequence
- 8. (weak/narrow AI) - AI trained to perform specific tasks based on what humans (we) currently know.
- 9. - Algorithm: a set of instructions to be followed in calculations or other operations
- 13. - When an AI system generates inaccurate information due to errors in its training or processing
- 14. - Occurs when training data is NOT representative of the real-world population & may lead to discriminatory outcomes
- 15. - Operates through pre-defined rules and logic. Outcomes based on relationships between symbols.
Down
- 1. - AI that truly mimics humans and is a true representation of ARTIFICIAL INTELLIGENCE
- 2. Type of AI that uses deep learning to analyze large amounts of data to perform natural language processing tasks
- 5. - Algorithms allow systems to improve performance when exposed to more data over time.
- 6. Learning - Subset of machine learning using deep neural networks with many layers. Allows for modeling of highly complex hierarchical patterns in data.
- 7. - mathematical representations of data, with magnitude and direction, that help machines understand and process information
- 10. - bias, lack of creativity, and difficulty understanding context
- 11. - Inspired by the design of the human brain, consists of layers of interconnected nodes or “neurons” that process input data through a network to produce an output.
- 12. - ANY form of recorded information: fingerprints, photos, audio recordings, text input, age, addresses, comments, emojis…