Audit glossary

Deep learning and neural networks

Models built from many layers of connected nodes that learn complex patterns.

AAIA

Deep neural networks power image recognition, speech and language models. They can be very accurate, but have millions or billions of parameters, which makes them hard to interpret.

On the exam

Deep learning trades interpretability for performance, so explainability controls matter more for high-impact decisions.

Related terms

  • ExplainabilityBeing able to say why an AI system produced a given output.
  • Machine learningSystems that learn patterns from data instead of following hand-written rules.
  • Generative AIAI that creates new content: text, images, code or audio.

AAIA Test yourself on this with timed AAIA practice questions in the AAIA Exam Simulation Hub, or read the free AAIA exam guide.

Test yourself with today’s question of the day.