# Content Domain 4: Machine Learning Implementation and Operations
<a name="machine-learning-specialty-01-domain4"></a>

**Topics**
+ [Task 4.1: Build ML solutions for performance, availability, scalability, resiliency, and fault tolerance](#machine-learning-specialty-01-domain4-task1)
+ [Task 4.2: Recommend and implement the appropriate ML services and features for a given problem](#machine-learning-specialty-01-domain4-task2)
+ [Task 4.3: Apply basic AWS security practices to ML solutions](#machine-learning-specialty-01-domain4-task3)
+ [Task 4.4: Deploy and operationalize ML solutions](#machine-learning-specialty-01-domain4-task4)

## Task 4.1: Build ML solutions for performance, availability, scalability, resiliency, and fault tolerance
<a name="machine-learning-specialty-01-domain4-task1"></a>
+ Log and monitor AWS environments.
  + AWS CloudTrail and Amazon CloudWatch
  + Build error monitoring solutions.
+ Deploy to multiple AWS Regions and multiple Availability Zones.
+ Create AMIs and golden images.
+ Create Docker containers.
+ Deploy Auto Scaling groups.
+ Rightsize resources (for example, instances, Provisioned IOPS, volumes).
+ Perform load balancing.
+ Follow AWS best practices.

## Task 4.2: Recommend and implement the appropriate ML services and features for a given problem
<a name="machine-learning-specialty-01-domain4-task2"></a>
+ ML on AWS (application services), for example:
  + Amazon Polly
  + Amazon Lex
  + Amazon Transcribe
  + Amazon Q
+ Understand AWS service quotas.
+ Determine when to build custom models and when to use Amazon SageMaker built-in algorithms.
+ Understand AWS infrastructure (for example, instance types) and cost considerations.
  + Use Spot Instances to train deep learning models by using AWS Batch.

## Task 4.3: Apply basic AWS security practices to ML solutions
<a name="machine-learning-specialty-01-domain4-task3"></a>
+ AWS Identity and Access Management (IAM)
+ S3 bucket policies
+ Security groups
+ VPCs
+ Encryption and anonymization

## Task 4.4: Deploy and operationalize ML solutions
<a name="machine-learning-specialty-01-domain4-task4"></a>
+ Expose endpoints and interact with them.
+ Understand ML models.
+ Perform A/B testing.
+ Retrain pipelines.
+ Debug and troubleshoot ML models.
  + Detect and mitigate drops in performance.
  + Monitor performance of the model.