DL-BASICS-NN

What is a neuron in the context of artificial neural networks (ANNs)?

• A hardware component

• A single processing unit

• A storage device

• A type of programming language

What is the purpose of the input layer in a neural network?

• To perform calculations

• To store data

• To receive data from external sources

• To visualize the output

What is the major limitation of a single-layer perceptron?

• It cannot process input data.

• It cannot solve non-linear problems.

• It requires more data storage.

• It has too many hidden layers.

Why do we use multi-layer neural networks?

• To solve linear problems only

• To classify non-linear data and solve complex problems

• To reduce the number of neurons

• To improve data storage capacity

What role do weights play in a neural network?

• They store data.

• They control the number of hidden layers.

• They determine the influence of inputs.

• They act as the final output.

What happens when you increase the number of hidden layers?

• The network becomes linear.

• The network loses its ability to generalize.

• The network stops training.

• The network can capture more complex patterns.

How is a perceptron different from a multi-layer perceptron (MLP)?

• MLP can solve non-linear problems, while perceptron cannot.

• Perceptron is faster than MLP.

• Perceptron has multiple hidden layers, while MLP has none.

• MLP stores more data than perceptron.

In a neural network, how does backpropagation help?

• By initializing weights randomly

• By preprocessing input data

• By updating weights to reduce error

• By predicting the output

Which activation function is commonly used in the hidden layer of an artificial neural network?

• Sigmoid

• Linear

• Tanh

• ReLU

In the basic implementation of an artificial neural network using Python, which library is most commonly used for neural network creation?

• Matplotlib

• NumPy

• TensorFlow

• Pandas