kaal:claim:4855607-003

Deep learning models inadvertently learn and amplify whatever biases exist in their training data, so the composition of the training corpus, not the architecture, is the source of unfair or discriminatory outcomes.

Depending on the data used for training, deep learning models can inadvertently learn and amplify biases present in the training data, potentially leading to unfair or discriminatory outcomes.

Wulf A. Kaal, How AI Models are Optimized Through Web3 Governance (2024), Model Overview: Deep Learning Models, p. 9
https://ssrn.com/abstract=4855607 · source PDF

Wulf A. Kaal, How AI Models are Optimized Through Web3 Governance (2024). SSRN: https://ssrn.com/abstract=4855607

• depends on the data used for training

failuresupport: evidencedfailure: Training data bias amplificationfamily: ai-model-and-training-failureai-and-agentseducation-and-practice

• generalizes kaal:claim:5245185-028 Anomaly detection and behavioral analysis models trained on agent data may replicate the biases in that data a...
• restated_by kaal:claim:4941807-015 A critical unsolved challenge for AI governance is bias mitigation, because biases enter inadvertently when al...
• generalizes kaal:claim:5541658-013 Bias in judicial AI arises because models are trained on historical data that reflect past inequities, and the...

The quote above is an exact substring of the source PDF, whose sha256 is eb0b3e62374b45a8fa888c6bde9725e606bcb46cf4b5e74a6e851d9f25099113. Extraction method: pdf-text-layer.
Attestation record: colloquium/attestations/32cc4a80d7ec5a23...json
Verify the binding yourself: curl -s https://wulfkaal.github.io/claims/4855607-003.md | sha256sum