Interactive explainers, hands-on labs, and real-world HCM use cases. Your guided path from ML fundamentals to production deployment.
Each module maps to a stage in the production ML pipeline. Follow the path from business goals to monitored models.
Click any available module to launch its interactive explainer. More modules are being built progressively.
AI hierarchy, ML lifecycle, training categories, SageMaker overview, responsible AI principles, and ML engineering roles.
Launch Explainer →Success criteria framework, supervised/unsupervised/reinforcement learning, classification, regression, clustering, and deep learning algorithms.
Launch Explainer →Data sources and quality, types and formats (CSV, Parquet, JSON), exploratory data analysis, AWS storage services (S3, EBS, EFS, FSx).
Launch Explainer →Data cleaning techniques, categorical encoding (binary, ordinal, one-hot), numeric scaling, feature selection, PCA, and AWS transformation services.
Launch Explainer →SageMaker built-in algorithms, Autopilot AutoML, algorithm selection by problem type, interpretability trade-offs, and ML cost optimization.
Launch Explainer →Loss functions, gradient descent, hyperparameters, SageMaker training jobs, compute options, Pipelines, Model Registry, and automatic tuning.
Launch Explainer →Bias-variance trade-off, confusion matrix, precision/recall/F1, ROC curves, early stopping, distributed training, and hyperparameter tuning strategies.
Launch Explainer →Deployment targets, blue/green and canary traffic shifting, inference options (real-time, serverless, async, batch), endpoint types, and cost optimization.
Launch Explainer →IAM roles and policies, VPC isolation, security groups, encryption with KMS, CI/CD pipeline security, and multi-country compliance for PII-heavy ML workloads.
Launch Explainer →MLOps fundamentals, CI/CD for ML, automated testing, AWS CodePipeline/CodeBuild/CodeDeploy, SageMaker Projects and Pipelines with quality gates.
Launch Explainer →Four types of drift, SageMaker Model Monitor, data/model quality monitoring, automated retraining with CloudWatch/SNS/Lambda/Step Functions.
Launch Explainer →Key takeaways, certification paths, next steps for building production ML systems, additional AWS learning resources.
Dedicated explainers for the key AWS services used across labs. Click to explore each service with interactive visualizations and HCM use cases.
Low-code data preparation: import, transform, analyze, and export datasets. 300+ built-in transforms. Lab 1 primary service.
ML workflow orchestration as a DAG. Step types, parameters, quality gates, Model Registry. Lab 6 primary service.
Model training jobs, built-in algorithms, hyperparameter tuning. Labs 3-4 primary service. Coming soon.
Lab guides, flow diagrams, and supplementary materials for the course.
Interactive visualization of all 7 labs covering the full ML lifecycle on AWS. Pipeline view, lab details, and lifecycle mapping.
Structured markdown summary of all lab objectives, task flows, and AWS services used across the 7 hands-on exercises.
Domain-specific ML examples mapped to HCM: payroll fraud detection, attrition prediction, salary benchmarking, document processing.