ML Crossword #3

1234567891011121314151617181920
Across
  1. 3. The primary data structure in TensorFlow programs
  2. 5. A model used as a reference point for comparing how well another model is performing
  3. 7. A linear model that typically has many sparse input features
  4. 9. Refers to your model's ability to make correct predictions on new, previously unseen data
  5. 13. A process that classifies object(s), pattern(s), or concept(s) in an image
  6. 14. A popular datatype for representing datasets in pandas
  7. 15. A variable of a model that the machine learning system trains on its own
  8. 17. The center of a cluster as determined by a k-means or k-median algorithm
  9. 18. A method for regularization that involves ending model training before training loss finishes decreasing
  10. 19. A node in a neural network, typically taking in multiple input values and generating one output value
  11. 20. A human who provides labels in examples
Down
  1. 1. A type of regularization that penalizes weights in proportion to the sum of the absolute values of the weights
  2. 2. Generating a group of predictions, storing those predictions, and then retrieving those predictions on demand
  3. 4. The recommended format for saving and recovering TensorFlow models
  4. 6. The fraction of predictions that a classification model got right
  5. 8. Producing a model with poor predictive ability because the model hasn't captured the complexity of the training data
  6. 10. A mathematical definition of “fairness” that is measurable
  7. 11. A quick solution to a problem, which may or may not be the best solution
  8. 12. An open-source Python 2D plotting library
  9. 16. The coordinates of particular features in an image