Introduction to Deep Learning

__________ plays a vital role in neural networks, and it is used to introduce non-linearity in neural networks.

An activation function

It implies backpropagating from the output layer to the input layer

Backward pass

It specifies the number of training samples we use in one forward pass and one backward pass

Batch size

It is a subset of Machine Learning inspired by the neural networks in the human brain.

Deep Learning

It is a modern name for artificial neural networks with many layers.

Deep Learning (ANN)

It specifies the number of times the neural network sees our whole training data

Epoch

It implies forward propagation from the input layer to the output layer

Forward pass

It implies the number of passes where one pass = one forward pass + one backward pass

Number of iterations

________ is basically the generalization of the sigmoid function. It is usually applied to the final layer of the network and while performing multi-class classification tasks.

The SoftMax function

_________ is one of the most commonly used activation functions. It scales the values between 0 and 1.

The sigmoid function

Although DL perform better than conventional ML models, it is not recommended to use Deep Learning for smaller datasets.

True - DL is not recommended for smaller datasets.

A neuron can be defined as the basic computational unit of the human brain.

True - It is the basic computational unit of the human brain

Any layer between the input layer and the output layer is called?

hidden layer