Aegis-GPU7.4 Minimizing bias
Where bias comes from and how to reduce it.
Key points
Bias is a systematic unfairness in model outputs. Narrow data teaches a narrow view of the world.
What NVIDIA says (1)
“AI models are trained by humans, often using data that is limited by size, scope and diversity.”
Synthetic data is generated data that can balance groups that are under-represented. Checking outputs for discriminatory patterns finds bias early.
What NVIDIA says (2)
“trustworthy AI developers mitigate potential unwanted bias by looking for clues and patterns that suggest an algorithm is discriminatory”
“Synthetic datasets offer one solution to reduce unwanted bias in training data”
Key terms
- Unwanted bias: Systematic unfairness in model outputs, often from narrow training data.
- Synthetic data: Generated data used to fill gaps in real data, including to reduce bias.
Sample question
Where does unwanted bias in AI often come from, per NVIDIA?
Show the answer
Answer: Training data limited in size, scope and diversity
Bias is a systematic unfairness in model outputs. Narrow data teaches a narrow view of the world.
What NVIDIA says (1)
“AI models are trained by humans, often using data that is limited by size, scope and diversity.”