Basics of Deep Learning

Front

What is Deep Learning?

Back

Deep Learning is a subfield of machine learning that uses artificial neural networks with many layers to learn representations from data.

Front

What is the key idea of Deep Learning?

Back

Learn features automatically from raw data, instead of hand-crafting them.

Front

How does a neural network process input data?

Back

Input data is fed into a neural network, where each neuron computes a weighted sum of its inputs, applies a non-linear activation function, and passes it on.

Front

What are the three types of layers in a neural network?

Back

Input Layer, Hidden Layers, Output Layer.

Front

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

Back

They are parameters the network learns to minimize errors.

Front

What is the role of activation functions in a neural network?

Back

They add non-linearity to the model.

Front

Name some common activation functions.

Back

ReLU, Sigmoid, Tanh, Softmax.

Front

What is a forward pass in training a neural network?

Back

It computes predictions.

Front

What does the loss function measure?

Back

It measures error, such as cross-entropy loss or mean squared error.

Front

What is backpropagation?

Back

It computes gradients of the loss with respect to weights.