Class Test_1_Neural Networks_Basics

Which of the following is a similarity between the human brain and an artificial neural network?

• Both can learn from experience.

• Both require labeled data for training.

• Both are fully deterministic.

• Both process information in serial order.

In what way does the human brain differ fundamentally from an artificial neural network?

• The brain processes information using electrical signals; neural networks use only software

• The brain uses neurons; neural networks use artificial neurons

• The brain operates in parallel, whereas neural networks process sequentially

• The brain has limited adaptability compared to neural networks

What is the primary goal of artificial neural networks compared to the human brain?

• To mimic cognitive processes for specific tasks.

• To mimic cognitive processes for specific tasks.

• To mimic cognitive processes for specific tasks.

• To mimic cognitive processes for specific tasks.

Which of the following statements is true?

• Neural networks are better at generalizing than the human brain.

• Neural networks can train without any external data.

• The human brain can adapt to unknown situations faster than neural networks.

• Neural networks do not require training iterations like the human brain.

What is the formula for calculating the net input to a neuron in a neural network?

• 
• 
• 

If a neuron has inputs x1=2, x2​=3, weights w1=0.5, w2=0.7, and bias b=−1, what is the net input?

• 3.6

• 2.6

• 1.6

• 0.6

Which of the following represents the purpose of weights in net input calculation?

• To normalize the input data.

• To adjust the importance of each input feature.

• To determine the activation threshold.

• To calculate the output directly

How do artificial neural networks learn from data?

• By adjusting weights based on error feedback.

• By simulating human emotions.

• By memorizing all input data.

• By using hard-coded rules.

Which of the following best describes the role of activation functions in neural networks?

• To increase the speed of data processing.

• To store the learned weights of the network.

• To normalize the input data before processing.

• To determine the output of a neuron based on its net input.

In a neural network, what is the purpose of the output layer?

• To compute the dot product of input features and weights

• To introduce non-linearity into the model

• To convert the output of neurons into predictions

• To initialize the weights of the network