Crash Course-AI#4

What are the two main parts of a neural network?

• Inputs and outputs

• Layers and nodes

• Architecture and weights

• Neurons and synapses

What is the purpose of backpropagation in neural networks?

• To add more neurons

• To adjust the weights to minimize error

• To remove unnecessary features

• To initialize the weights

In the metaphor of optimization, what does the altitude represent?

• The number of neurons

• The number of features

• The learning rate

• The error of the neural network

What is overfitting in the context of neural networks?

• When the network has too many layers

• When the network has too few features

• When the network fits the training data too well

• When the network is too simple

How can overfitting be prevented?

• By adding more features

• By keeping the neural network simple

• By using more training data

• By increasing the learning rate