AI facts & stats

Question 1

What is machine learning?

Accepted Answer

Computers learning patterns from data instead of following only fixed rules. Machine learning lets systems improve at tasks by finding patterns in data.

Question 2

Artificial neural networks were inspired by what?

Accepted Answer

Neurons in the brain. Artificial neural networks loosely mimic how brain neurons connect and pass signals.

Question 3

Supervised learning trains a model using what?

Accepted Answer

Labeled examples with known answers. In supervised learning, each training example comes with the correct label the model learns to predict.

Question 4

Grouping similar data points without any labels is an example of which approach?

Accepted Answer

Unsupervised learning (clustering). Clustering is unsupervised: the algorithm finds groups in data without being told the answers.

Question 5

What makes deep learning "deep"?

Accepted Answer

Neural networks with many layers. Deep learning uses neural networks with many stacked layers that learn increasingly complex features.

Question 6

The Transformer architecture was introduced in a 2017 paper with what title?

Accepted Answer

Attention Is All You Need. The 2017 paper 'Attention Is All You Need' introduced the Transformer, built around attention mechanisms.

Question 7

What does gradient descent do when training a model?

Accepted Answer

Adjusts parameters step by step to reduce error. Gradient descent moves parameters in the direction that most reduces the loss, a little at a time.

AI facts & stats

The basics