Neural network architecture in ML Python - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is a neural network architecture?

It is the design or layout of a neural network, showing how layers and neurons connect to process information.

beginner

Name the three main types of layers in a simple neural network.

Input layer, hidden layer(s), and output layer.

intermediate

What role do activation functions play in neural networks?

They help the network learn complex patterns by adding non-linearity to the output of neurons.

intermediate

Explain the difference between a shallow and a deep neural network.

A shallow network has few hidden layers, while a deep network has many hidden layers, allowing it to learn more complex features.

beginner

What is the purpose of weights and biases in a neural network?

Weights control the strength of connections between neurons, and biases allow shifting the activation function to better fit data.

Which layer in a neural network receives the raw input data?

A Activation layer

B Hidden layer

C Output layer

D Input layer

The input layer is where the network receives the raw data to start processing.

What does adding more hidden layers to a neural network usually allow it to do?

A Learn simpler patterns

B Reduce training time

C Learn more complex patterns

D Avoid overfitting

More hidden layers help the network learn complex features and patterns in data.

Which of these is NOT a common activation function?

A ReLU

B Linear Regression

C Softmax

D Sigmoid

Linear Regression is a model, not an activation function.

What do weights in a neural network represent?

A The strength of connections between neurons

B The input data

C The output predictions

D The number of layers

Weights control how much influence one neuron has on another.

Why do neural networks use biases?

A To shift activation functions for better learning

B To reduce the number of neurons

C To store input data

D To add randomness

Biases help adjust the output of neurons to better fit the data.

Describe the basic structure of a neural network and the role of each layer.

Think about how data enters, gets processed, and then produces results.

Explain why activation functions are important in neural networks.

Consider what would happen if neurons only did simple math without activation.