For Beginners Flashcards
7 cards from real AI practice questions. Tap to flip, then mark Knew It or Still Learning — missed cards come back until you master them.
Read the first 7 For Beginners flashcards as text
What does the acronym 'GPU' stand for, and why is it important for AI training?
Answer: Graphics Processing Unit; its massively parallel architecture accelerates matrix operations
GPUs contain thousands of small cores designed for parallel computation, making them far faster than CPUs for the matrix math in deep learning.
Which loss function is typically used for multi-class classification problems?
Answer: Categorical Cross-Entropy
Categorical cross-entropy measures the divergence between predicted class probabilities and the one-hot true labels across multiple classes.
What is the purpose of the softmax function in the output layer of a neural network?
Answer: To convert raw logits into a probability distribution summing to 1
Softmax exponentiates each logit and divides by the sum, producing non-negative class probabilities that sum to exactly 1.
In natural language processing, what does 'tokenization' refer to?
Answer: Splitting raw text into smaller units such as words or subwords
Tokenization breaks text into tokens (words, subwords, or characters) that serve as the discrete input units for NLP models.
What is the k-nearest neighbors (k-NN) algorithm?
Answer: A non-parametric method that classifies a point based on the majority label of its k closest training examples
k-NN assigns the label voted by the k training samples nearest to a query point, with no explicit model learned.
Which of the following is a key advantage of using a pre-trained large language model (LLM) over training from scratch?
Answer: LLMs provide rich prior knowledge, drastically reducing data and compute needed for a target task
Pre-trained LLMs encode broad world knowledge from massive corpora, so fine-tuning them needs far fewer labeled examples and compute than training from scratch.
What does 'epoch' mean in the context of training a machine learning model?
Answer: One complete pass through the entire training dataset
One epoch means the model has seen every training example exactly once; multiple epochs repeat this process to improve learning.