https://www.rubythalib.com/ml-on-production.html

Start : 16 Juni , 2024

Setiap Minggu: 08.00-10.00 WIB

What You Get in AI Online Class

- Interactive Class

​- Live Question and Answer with Mentor

- e-Certificate

- Portfolio

- Interactive Class

Material:

Session 1 : Introduction to Machine Learning on Production

Overview of Machine Learning (ML) lifecycle

Challenges in deploying ML models to production

Importance of ML in real-world applications

Introduction to production-grade ML systems

Case studies of successful ML deployments

Session 2 : Data Preparation and Preprocessing

Data collection and storage for production systems

Data cleaning and preprocessing techniques

Feature engineering for production environments

Handling missing values and outliers

Data versioning and management strategies

​

Session 3 : Model Development and Evaluation

Choosing appropriate ML algorithms for production

Model training and evaluation best practices

Hyperparameter tuning for production models

Techniques for model interpretability and explainability

A/B testing and evaluation metrics for production models

Session 4 : Scalable Infrastructure for ML

Introduction to scalable ML infrastructure

Cloud computing platforms for ML in production

Containerization and orchestration (e.g., Docker, Kubernetes)

Scalable data processing frameworks (e.g., Apache Spark)

Managing infrastructure costs and resources

Session 5 : Deployment Strategies

Strategies for deploying ML models in production

Model serving and inference pipelines

Monitoring and logging for deployed models

Continuous integration and continuous deployment (CI/CD)

Blue-green deployments and canary releases

Session 6 : Model Maintenance and Lifecycle Management

Importance of model maintenance in production

Strategies for model retraining and updating

Versioning and rollback mechanisms

Ethical considerations in model lifecycle management

Case studies and real-world examples of model maintenance challenges