1. In an ANN, the function that introduces non-linearity is called the __________.

1. The process of adjusting weights based on error gradients is called __________.

1. The __________ layer in an ANN receives raw input features.

1. Overfitting in ANN can be reduced using a technique called __________, where random neurons are ignored during training.

1. The universal function approximation theorem states that an ANN with at least one hidden layer can approximate any __________ functions.

1. The __________ algorithm is a variant of gradient descent that includes momentum and adaptive learning rates.

1. In an ANN, the sum of weighted inputs plus bias is passed through an __________ to produce the output of a neuron.

1. A neural network without hidden layers is equivalent to performing __________ regression.

1. The __________ function is commonly used for binary classification problems in ANN.

1. In ANN, the weights are updated using the rule: New Weight = Old Weight – __________ × Gradient.