AI engineering glossary · Deep learning core
What is multi-task learning?
Multi-task learning: Training a single network to solve several related tasks at once, sharing early layers and using separate output heads. Shared representations can improve accuracy and data efficiency on each task.
Multi-task learning: an example
One shared network might predict both sentiment and product category of a review.
Related terms
More Deep learning core terms
- Multilayer perceptron
- Negative log-likelihood
- Neural network pruning
- Neural tangent kernel
- Neuron
- One-cycle policy
- Optimiser
- Orthogonal initialisation
Where you learn it
Multi-task learning is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.