ML corssword #8

3. a state reached during training in which training loss and validation loss change very little with each iteration
4. The portion of a Long Short-Term Memory cell that regulates the flow of information through the cell
6. The center of a cluster as determined by a k-means or k-median algorithm
7. A generalization of Log Loss to multi-class classification problems
9. An N-gram in which N=2
10. The number of layers in a neural network that learn weights
11. A specialized hardware accelerator designed to speed up machine learning workloads on Google Cloud Platform
12. Data that captures the state of the variables of a model at a particular time

1. A system that determines whether examples are real or fake
2. A sophisticated gradient descent algorithm that rescales the gradients of each parameter
3. In mathematics, casually speaking, a mixture of two functions
5. A categorical feature represented as a continuous-valued feature
7. A technique for handling outliers
8. In reinforcement learning, each of the repeated attempts by the agent to learn an environment.