Deep Learning Quiz

What is the basic unit of a biological neuron modeled in artificial neural networks?

• Synapse

• Axon

• Perceptron

• Dendrite

What is the primary function of the activation function in a perceptron?

• To initialize weights

• To determine whether a neuron should be activated

• To calculate the gradient

• To minimize the loss function

In a feed-forward neural network, how is information propagated through the network?

• Backward, from output to input

• In a circular manner

• Forward, from input to output

• Randomly between layers

What learning algorithm is typically used to update weights in a neural network during training?

• Backpropagation

• Genetic algorithm

• K-means

• Decision trees

What is the purpose of the loss function in training neural networks?

• To stop training when it reaches zero

• To evaluate the performance of the model by measuring the difference between the predicted and actual output

• To determine the network capacity

• To initialize weights

What term refers to the settings that control the learning process, such as learning rate, batch size, and number of epochs?

• Parameters

• Hyperparameters

• Weights

• Biases

What problem occurs when a model fits the training data too well, capturing noise rather than general patterns?

• Underfitting

• Overfitting

• Bias

• Gradient explosion

Which of the following techniques helps prevent overfitting in deep networks?

• Stochastic gradient descent

• Increasing the batch size

• Regularization methods like dropout or L2 regularization

• Using a single-layer network

Which optimization technique updates the model parameters using only a small subset of the data in each iteration?

• Gradient descent

• Stochastic gradient descent (SGD)

• Simulated annealing

• Backpropagation

What happens when a model is too simple to capture the underlying pattern in the data, leading to poor performance on both training and test data?

• Overfitting

• Underfitting

• Regularization

• Gradient saturation