Your next step

Different ways to learn

Find where a training setup's signal comes from.

What you’ll learn

Learning with supplied answers
Identify supervised learning from paired examples and targets.
About 4 minutes · Open activity
Learning without supplied answers
Identify unsupervised learning from unlabelled examples.
About 4 minutes · Open activity
Making a practice question from the data
Explain self-supervision using a hidden part of an example.
About 4 minutes · Open activity
Predicting what comes next
Identify the target in a next-piece training example.
About 4 minutes · Open activity
Matching things that belong together
Recognize a contrastive training task.
About 4 minutes · Open activity
Learning through consequences
Identify reinforcement learning from action and outcome feedback.
About 4 minutes · Open activity
The score is a design choice
Separate a reward from the real intention.
About 4 minutes · Open activity
A small labeled set can guide a larger collection
Recognize semi-supervised learning from mixed labeled and unlabeled examples.
About 4 minutes · Open activity
Methods can be combined
Recognize successive learning methods in one model's development.
About 4 minutes · Open activity
Find the learning signal
Inspect three training setups, identify the target or feedback source in each, and repair one badly chosen reward.
About 6 minutes · Open activity