AWS wellarchitected documentation change
Summary
Fixed typo in 'offline', updated figure numbering from 14 to 13, simplified image description, and changed final section header from 'Operational excellence pillar best practices' to 'Deployment'.
Security assessment
Changes are editorial corrections and figure updates without security implications. No security-related content added or modified in model evaluation context.
Diff
diff --git a/wellarchitected/latest/machine-learning-lens/model-evaluation.md b/wellarchitected/latest/machine-learning-lens/model-evaluation.md index af1a41a6d..efc5d7301 100644 --- a//wellarchitected/latest/machine-learning-lens/model-evaluation.md +++ b//wellarchitected/latest/machine-learning-lens/model-evaluation.md @@ -9 +9 @@ After the model has been trained, evaluate it for its performance and success me -You can evaluate your model using historical data (offline evaluation) or live data (online evaluation). In offline evaluation, the trained model is evaluated with a portion of the dataset that has been set aside as a _holdout set_. This holdout data is never used for model training or validation-it’s only used to evaluate errors in the final model. The holdout data annotations must have high assigned label correctness for the evaluation to make sense. Allocate additional resources to verify the correctness of the holdout data. +You can evaluate your model using historical data (offline evaluation) or live data (online evaluation). In offline evaluation, the trained model is evaluated with a portion of the dataset that has been set aside as a _holdout set_. This holdout data is never used for model training or validation, but rather to evaluate errors in the final model. The holdout data annotations must have high assigned label correctness for the evaluation to make sense. Allocate additional resources to verify the correctness of the holdout data. @@ -13 +13 @@ Based on the evaluation results, you might fine-tune the data, the algorithm, or - + @@ -15 +15 @@ Based on the evaluation results, you might fine-tune the data, the algorithm, or -_Figure 14: ML lifecycle with performance evaluation pipeline added_ +_Figure 13: ML lifecycle with performance evaluation pipeline added_ @@ -17 +17 @@ _Figure 14: ML lifecycle with performance evaluation pipeline added_ -Figure 14 includes the model performance evaluation, the _data prepare_ and CI/CD/CT pipelines that fine-tune data and/or algorithm, re-training, and evaluation of model results. +Figure 13 includes the model performance evaluation, the _data prepare_ and CI/CD/CT pipelines that fine-tune data and algorithms, re-training, and evaluation of model results. @@ -27 +27 @@ Model training and tuning -Operational excellence pillar best practices +Deployment