Across
- 4. Function used to convert logits to probabilities in multi-class classification
- 6. Popular activation function that outputs 0 for negative inputs and the input itself for positive inputs
- 7. Neural network architecture designed for sequence data
- 9. A supervised learning algorithm often used for classification tasks
- 12. Algorithm that separates data using a hyperplane
- 13. Process by which neural networks learn, adjusting weights based on errors
Down
- 1. A problem where a model fits training data too closely and fails to generalize
- 2. Learning paradigm where the model learns from feedback and rewards
- 3. Preprocessing step to bring data to a common scale
- 5. ML task to predict numerical outcomes
- 8. Popular deep learning framework by Google
- 10. An unsupervised learning algorithm that groups data into clusters
- 11. Statistical method to reduce dimensionality
- 14. Type of neural network commonly used in image processing
