1. What is the basic purpose of an artificial neural network?
2. Which part of an artificial neuron receives input values?
3. What is the main purpose of a weight in a neural network?
4. What is the role of bias in an artificial neuron?
5. Which expression represents the weighted sum of inputs in a neuron?
6. A neuron has inputs 2, 3 and 1 with weights 0.4, 0.2 and 0.6 respectively, and bias 0.1. What is the weighted sum including bias?
7. What is the main purpose of an activation function?
8. Which activation function produces either 0 or 1 depending on whether a threshold is reached?
9. Which activation function outputs values between 0 and 1 and is commonly associated with probability-like outputs?
10. What does forward propagation mean in a neural network?
11. What is the primary purpose of backpropagation?
12. What is generally calculated to determine how different a prediction is from the actual value?
13. Which type of neural network passes information from input toward output without forming cycles?
14. Which neural network architecture is particularly useful for processing image data?
15. What is a key feature of a Convolutional Neural Network?
16. Which neural network is particularly suited to sequential or time-dependent data?
17. What is a characteristic feature of an RNN?
18. What is the main purpose of a Generative Adversarial Network?
19. Which two components compete with each other in a GAN?
20. What is the role of the discriminator in a GAN?
21. Which statement best describes a perceptron?
22. If increasing the value of a weight makes an input contribute more strongly to a neuron’s weighted sum, what does the weight represent?
23. Why are hidden layers called “hidden” layers?
24. What happens when a neural network is trained?
25. Which sequence correctly represents the basic flow during forward propagation?
26. Suppose a neuron calculates a weighted sum of 1.5 and has a bias of 0.5. What is the resulting value before applying an activation function?
27. Which application is most naturally associated with an RNN?
28. Why is responsible use of neural-network technology important?
29. What can happen if the training data used by a neural network contains significant bias?
30. Which combination correctly matches the neural-network type with a suitable application?
