Multi-class classification model in TensorFlow - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is a multi-class classification model?

A multi-class classification model is a type of machine learning model that can classify input data into more than two categories or classes.

beginner

Which activation function is commonly used in the output layer of a multi-class classification model?

The softmax activation function is commonly used in the output layer to convert raw scores into probabilities for each class.

intermediate

Why do we use categorical cross-entropy loss in multi-class classification?

Categorical cross-entropy measures the difference between the true class labels and the predicted probabilities, helping the model learn to predict the correct class.

beginner

How does the model output look like in multi-class classification?

The model outputs a probability distribution over all classes, where each value represents the probability that the input belongs to that class, and all probabilities sum to 1.

beginner

What metric is commonly used to evaluate multi-class classification models?

Accuracy is commonly used, which measures the percentage of correct predictions out of all predictions made.

Which activation function is best for the output layer in a multi-class classification model?

A Softmax

B ReLU

C Sigmoid

D Tanh

Softmax converts outputs into probabilities that sum to 1, which is ideal for multi-class classification.

What loss function is typically used for multi-class classification?

A Mean Squared Error

B Hinge Loss

C Binary Cross-Entropy

D Categorical Cross-Entropy

Categorical Cross-Entropy is designed to compare predicted probabilities with true class labels in multi-class problems.

In multi-class classification, the model's output layer size should be:

A Number of classes neurons

B 1 neuron

C Number of features neurons

D Half the number of classes neurons

The output layer has one neuron per class to predict the probability for each class.

What does the softmax function do?

A Outputs raw scores

B Outputs probabilities summing to 1

C Outputs binary values

D Outputs negative values

Softmax converts raw scores into probabilities that sum to 1 across classes.

Which metric tells how many predictions were correct in multi-class classification?

A Loss

B Precision

C Accuracy

D Recall

Accuracy measures the percentage of correct predictions out of total predictions.

Explain how a multi-class classification model works from input to output.

Think about how the model turns input data into a class prediction.

Describe why softmax and categorical cross-entropy are used together in multi-class classification.

Consider how the model learns from its predictions.