Glossary AI Safety 1 min read

Bias in AI

Also known as: Algorithmic Bias, AI Bias, Machine Learning Bias

Systematic errors in AI system outputs that create unfair outcomes for certain groups, typically arising from biased training data, flawed model design, or biased evaluation metrics.

Fairness, discrimination, algorithmic bias, data bias, representation bias, selection bias, measurement bias, confirmation bias, societal bias, debiasing, equitable AI, bias mitigation, disparate impact, protected attributes, fairness metrics

Sources & References

1
Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification

MIT Media Lab

Research
2
Bias in AI and Machine Learning

National Institute of Standards and Technology

Government
3
Fairness and Machine Learning

Solon Barocas, Moritz Hardt, Arvind Narayanan

Related Terms

AI Alignment

The research field focused on ensuring that AI systems' goals, behaviors, and values are compatible with human intentions and societal well-being throughout their operation.

AI Governance

The frameworks, policies, standards, and oversight mechanisms that guide the development, deployment, and use of AI systems within organizations and across society.

Responsible AI

The practice of designing, developing, deploying, and using AI systems in ways that are ethical, transparent, fair, accountable, and aligned with human rights and societal values.

Training Data

The curated dataset used to train machine learning models, whose quality, diversity, size, and representativeness directly determine the model's capabilities and limitations.
Previous Batch Processing Optimizer
Next Bridge Adapter Framework
Back to Glossary