Machine learning

Can we teach computers to learn like humans?

Imagine you're trying to teach a child to recognize different fruits by showing them pictures and telling them what they are. You start with easy ones like apples and gradually introduce more complex ones like persimmons.

Curriculum learning is like starting with simple fruits and slowly moving to harder ones, helping the child learn better by building on what they already know.

Example

First, you show the child 10 apple pictures, then 10 orange pictures, and gradually add more complex fruits.

Remember this

It's about teaching machines in a step-by-step way, starting simple and gradually increasing complexity.

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

Related concepts

Glossary of artificial intelligence

Can computers learn to mimic human brain functions?

instruction tuning does: fine-tunes on (instruction, response) pairs

Fine-tuning adapts pre-trained models to new tasks

Prompt engineering

The GenAI model learns tasks from examples in the prompt

soft targets carry more information than hard labels: they encode class similarities

Why do some learning methods need to explore more than others?

Knowledge distillation

Knowledge distillation transfers knowledge from a large model to a smaller one without loss of validity

data augmentation does for generalization: artificially expands training set

How can you teach a computer to see better?

Swipe through 100 ML concepts daily

Open Pocket Polymath