Glossary of artificial intelligence

Can computers learn to mimic human brain functions?

Imagine you're trying to teach a computer to recognize different types of fruit in photos. You want it to get better over time as it sees more examples.

Think of a neural network as a group of interconnected brain cells that learn from experience. Each connection strengthens as the computer sees more fruit photos, helping it to recognize new ones more accurately.

Example

If the computer starts with 10 fruit photos of apples and bananas, and then sees 100 more, it gets better at telling them apart after seeing all 110 photos.

Remember this

Neural networks can improve their accuracy over time, making them good at tasks like recognizing fruit in photos.

Text adapted from Wikipedia, licensed under CC BY-SA 4.0.

Related concepts

Machine learning

Can we teach computers to learn like humans?

dropout works as regularization: it approximates an ensemble of subnetworks

Why does turning off neurons randomly help a brainy computer learn better?

Physics-informed neural networks

Neural ODEs model continuous-time dynamics with a neural network as the derivative

Convolutional neural network

Can a neural network learn too well?

MoE models have more parameters but similar compute cost

MoE models distribute parameters across k experts, reducing active experts' compute cost

approximation algorithms guarantee: solution within factor α of optimal

Can we always find the best solution quickly?

Swipe through 100 ML concepts daily

Open Pocket Polymath