AI For Beginners 4

Question 1

What does the acronym 'GPU' stand for, and why is it important for AI training?

Accepted Answer

Graphics Processing Unit; its massively parallel architecture accelerates matrix operations

Answer

GPUs contain thousands of small cores designed for parallel computation, making them far faster than CPUs for the matrix math in deep learning.

Question 2

Which loss function is typically used for multi-class classification problems?

Accepted Answer

Categorical Cross-Entropy

Answer

Categorical cross-entropy measures the divergence between predicted class probabilities and the one-hot true labels across multiple classes.

Question 3

What is the purpose of the softmax function in the output layer of a neural network?

Accepted Answer

To convert raw logits into a probability distribution summing to 1

Answer

Softmax exponentiates each logit and divides by the sum, producing non-negative class probabilities that sum to exactly 1.

Question 4

In natural language processing, what does 'tokenization' refer to?

Accepted Answer

Splitting raw text into smaller units such as words or subwords

Answer

Tokenization breaks text into tokens (words, subwords, or characters) that serve as the discrete input units for NLP models.

Question 5

What is the k-nearest neighbors (k-NN) algorithm?

Accepted Answer

A non-parametric method that classifies a point based on the majority label of its k closest training examples

Answer

k-NN assigns the label voted by the k training samples nearest to a query point, with no explicit model learned.

AI - Engineer Practice Test