1. Introduction to Neural Networks and Deep Learning (Chapter 1)

1. What is a perceptron in neural networks, and how does it work? - a) A perceptron is a multi-layer neural network with multiple activation functions.

• b) A perceptron is the simplest type of neural network, consisting of a single layer that makes decisions based on linear combinations of the inputs.
• c) A perceptron is a deep learning algorithm designed for complex pattern recognition tasks.
• d) A perceptron is used only in unsupervised learning for clustering tasks.

1. Which of the following is NOT a technique for reducing overfitting in neural networks? - a) Dropout

• b) Early Stopping
• c) Increasing the number of layers
• d) L2 Regularization

1. What is the purpose of the softmax activation function in the output layer of a neural network? - a) To produce a binary output for classification tasks.

• b) To map output values to the range [-1, 1].
• c) To output probabilities for multi-class classification problems.
• d) To minimize the loss during backpropagation.