Part 6

What is the core component of a Multilayer Perceptron (MLP) that receives input features?

• Input Layer

• Hidden Layers

• Output Layer

• Weight Matrices

Which type of artificial neural network is a Multilayer Perceptron (MLP)?

• Convolutional Neural Network (CNN)

• Recurrent Neural Network (RNN)

• Deep Neural Network (DNN)

• Generative Adversarial Network (GAN)

What is the purpose of activation functions in MLPs?

• To introduce non-linearity

• To use linear assumptions

• To reduce the learning rate

• To reach overfitting

Which type of connection pattern connects each neuron in one layer to all neurons in the next layer?

• Fully Connected

• Partially Connected

• Randomly Connected

• Sequentially Connected

What is the purpose of non-linear activation functions in MLPs?

• To enable neural networks to learn complex patterns

• To compute weighted sums of different architectures

• To introduce linearity

• To produce the final random output

Which activation function is commonly used in the output layer of an MLP for classification tasks?

• Sigmoid

• Tanh

• ReLU

• Softmax

What is the formula for the sigmoid activation function?

• f(x) = 1 / (1 + e^(-x))

• f(x) = tanh(x)

• f(x) = max(0, x)

• f(x) = x

Which activation function ranges from -1 to 1 and is may preferred in hidden layers of DNNs?

• Sigmoid

• Tanh

• ReLU

• Softmax

What are the advantages of the ReLU activation function over sigmoid and tanh?

• Addresses vanishing gradient problem

• Produces output between 0 and 1

• Enables neural networks to reduce learning rate

• Faster to compute

What is the typical drawback of the ReLU activation function?

• Vanishing gradient problem

• Increasing learning rate

• Dying ReLU problem (inactive neurons)

• High computational cost