AWS Certified Machine Learning Engineer Associate (MLA-C01) Cert Prep
25h 2mIntermediate2025-06-04
Authors
Digital Cloud Training
Karim El-Kobrossy
Course details
The AWS Certified Machine Learning Engineer - Associate exam validates your ability to build, operationalize, deploy, and maintain machine learning (ML) solutions and pipelines by using the AWS Cloud. Prepare for the exam with this course by learning how to: ingest, transform, validate, and prepare data for ML modeling; select general modeling approaches, train models, tune hyperparameters, analyze model performance, and manage model versions; choose deployment infrastructure and endpoints, provision compute resources, and configure auto scaling based on requirements; set up continuous integration and continuous delivery (CI/CD) pipelines to automate orchestration of ML workflows; monitor models, data, and infrastructure to detect issues; and secure ML systems and resources through access controls, compliance features, and best practices.
Skills covered
Machine LearningCloud ServicesCloud PlatformsCert PrepArtificial Intelligence (AI)Cloud Computing
Concepts
0. Introduction
- 01 - Introduction to MLA
1. Data Storage and Ingestion
- 02 - Intro - Data storage and ingestion
- 03 - The three Vs
- 04 - Types of data
- 05 - Batch versus streaming
- 06 - OLTP vs. OLAP
- 07 - Data formats
- 08 - Data modeling
- 09 - Data warehouses
- 10 - Data lakes
- 11 - Data ingestion scenarios
- 12 - Amazon FSx
- 13 - Hands-on learning - Loading data into model training resource
- 14 - Amazon Kinesis Data Streams
- 15 - Hands-on learning - Create a data stream
- 16 - Using EFS with Lambda
- 17 - Hands-on learning - Create an AWS Lambda function to consume a Kinesis Data Stream
- 18 - Amazon Kinesis Client Library (KCL)
- 19 - Apache Kafka
- 20 - Amazon MSK
- 21 - Kinesis vs. MSK
- 22 - Amazon Data Firehose
- 23 - Hands-on learning - Configure an Amazon Data Firehose stream
- 24 - Amazon Managed Service for Apache Flink
- 25 - Amazon Kinesis Analytics
- 26 - Amazon Kinesis Video Streams
- 27 - Amazon Redshift
- 28 - Amazon Redshift Serverless
- 29 - Storage platforms
- 30 - Aligning to access patterns
- 31 - Cost and performance comparisons
- 32 - Extracting data from storage
- 33 - Summary of storage options
- 34 - Exam cram
2. Exploratory Data Analysis
- 35 - Intro - Exploratory data analysis
- 36 - Plots
- 37 - Data types
- 38 - Data distribution
- 39 - Feature engineering
- 40 - Data transformation (numbers-categories)
- 41 - Data transformation (text-images)
- 42 - Imputation techniques
- 43 - Unbalanced data
- 44 - Outliers
- 45 - Amazon EMR introduction
- 46 - Apache Hadoop
- 47 - Hadoop frameworks
- 48 - Apache Spark
- 49 - Amazon EMR architecture
- 50 - Hands-on learning - Launch an EMR cluster
- 51 - Transforming streaming data (Lambda and Spark)
- 52 - EMR Serverless
- 53 - Amazon SageMaker Feature Store
- 54 - AWS Glue
- 55 - Hands-on learning - AWS Glue (crawler and transformation)
- 56 - AWS Glue Data Catalog
- 57 - Hands-on learning - Create an AWS Glue Data Catalog
- 58 - AWS Glue DataBrew
- 59 - Hands-on learning - Create a DataBrew project
- 60 - Amazon Athena
- 61 - Hands-on learning - Running SQL queries in Athena
- 62 - Exam cram
3. Machine Learning
- 63 - Intro - Machine learning
- 64 - Taxonomy of AI
- 65 - Traditional vs. AI methods for solving problems
- 66 - AI real-world applications
- 67 - Business view for AI
- 68 - Sources of ML models
- 69 - Machine learning categories
- 70 - Regression
- 71 - Regression-model evaluation
- 72 - Classification
- 73 - Classification-model evaluation
- 74 - Dimensionality reduction
- 75 - Deep learning
- 76 - Natural language processing (NLP)
- 77 - Computer vision (CV)
- 78 - Convolutional neural network (CNN)
- 79 - Recurrent neural network
- 80 - Advancements in NLP
- 81 - Neural network characteristics
- 82 - Neural networks' problems
- 83 - Overfitting and underfitting
- 84 - Preventing overfitting
- 85 - Validation techniques
- 86 - Decision trees
- 87 - Ensemble learning
- 88 - Reducing model size
- 89 - Performance, training time, and cost tradeoffs
- 90 - AI use cases
- 91 - Interpreting ML models
- 92 - Exam cram
4. Managed AI Services
- 93 - Intro - Managed AI services
- 94 - AI services
- 95 - Amazon Comprehend
- 96 - Hands-on learning - Customer reviews sentiment analysis
- 97 - Amazon Translate
- 98 - Hands-on learning - Amazon Translate
- 99 - Amazon Transcribe
- 100 - Hands-on learning - Amazon Transcribe
- 101 - Amazon Polly
- 102 - Hands-on learning - Amazon Polly
- 103 - Amazon Rekognition
- 104 - Hands-on learning - Amazon Rekognition
- 105 - Amazon Textract
- 106 - Hands-on learning - Amazon Textract
- 107 - Amazon Forecast
- 108 - Amazon Lex
- 109 - Amazon Fraud Detector
- 110 - Amazon Personalize
- 111 - Amazon Kendra
- 112 - Hands-on learning - Amazon Kendra
- 113 - Amazon Bedrock
- 114 - Hands-on learning - PartyRock (Amazon Bedrock playground)
- 115 - Amazon Augmented AI
- 116 - EC2 instances for AI
- 117 - Amazon Q Business
- 118 - Amazon Q Apps
- 119 - Hands-on learning - Amazon Q Business
- 120 - Hands-on learning - Amazon Q Apps
- 121 - Amazon Q Developer
- 122 - Exam cram
5. Modelling (SageMaker Built-In Algorithms)
- 123 - Intro - Modelling (SageMaker built-in algorithms)
- 124 - Amazon SageMaker, SageMaker Studio
- 125 - Hands-on learning - Amazon SageMaker walkthrough
- 126 - Hands-on learning - Create an Amazon SageMaker notebook instance
- 127 - Built-in algorithms overview
- 128 - Linear Learner
- 129 - XGBoost
- 130 - LightGBM
- 131 - K-Nearest Neighbours
- 132 - Factorization Machines
- 133 - DeepAR
- 134 - Image classification
- 135 - Object detection
- 136 - Semantic segmentation
- 137 - Seq2Seq
- 138 - BlazingText
- 139 - Neural Topic Model (NTM)
- 140 - Latent Dirichlet Allocation (LDA)
- 141 - Random Cut Forest (RCF)
- 142 - K-means clustering
- 143 - Hierarchical clustering
- 144 - Object2Vec
- 145 - Principal Component Analysis (PCA)
- 146 - IP Insights
- 147 - Reinforcement learning
- 148 - Built-in algorithms recap
- 149 - Hyperparameter tuning (automatic model tuning)
- 150 - Hands-on learning - Hyperparameter tuning job
- 151 - Exam cram
6. Amazon SageMaker Services
- 152 - Intro - Amazon SageMaker services
- 153 - Amazon SageMaker Ground Truth
- 154 - Hands-on learning - Create a labelling job
- 155 - SageMaker Data Wrangler
- 156 - Hands-on learning - SageMaker Data Wrangler
- 157 - SageMaker Model Monitor
- 158 - Bias in machine learning
- 159 - Amazon SageMaker Clarify
- 160 - Hands-on learning - Amazon SageMaker Clarify
- 161 - Amazon SageMaker Feature Store
- 162 - SageMaker Canvas
- 163 - Hands-on learning - SageMaker Canvas
- 164 - SageMaker Model Registry
- 165 - Exam cram
7. Model Deployment
- 166 - Intro - Model deployment
- 167 - Online inference (real-time)
- 168 - Batch transform
- 169 - Other deployments
- 170 - Multi-model vs. multi-container endpoints
- 171 - Hands-on learning - Multi-model endpoint
- 172 - Hands-on learning - Multi-container endpoint
- 173 - SageMaker deployment
- 174 - Hands-on learning - XGBoost (churn prediction)
- 175 - Hands-on learning - Script mode
- 176 - Hands-on learning - Bring your own (BYO) Docker
- 177 - SageMaker instance types
- 178 - SageMaker SDK
- 179 - Distributed training
- 180 - SageMaker Debugger
- 181 - Hands-on learning - SageMaker serverless inference
- 182 - SageMaker Autopilot
- 183 - Amazon SageMaker Inference Recommender
- 184 - Amazon SageMaker Serverless Inference
- 185 - Inference pipeline
- 186 - Hands-on learning - SageMaker Model Monitor
- 187 - SageMaker Neo
- 188 - SageMaker security
- 189 - Deployment target services
- 190 - Maintainable, scalable, cost-effective deployments
- 191 - Automatic scaling metrics
- 192 - Performance tradeoff analysis
- 193 - Apache Airflow, SageMaker Pipelines
- 194 - Isolated ML system
- 195 - Exam cram
8. AWS Infrastructure, MLOps, and Orchestration
- 196 - Intro - AWS infrastructure, MLOps, and orchestration
- 197 - On-demand vs. provisioned resources
- 198 - Scaling policies
- 199 - Infrastructure as code (IaC) services
- 200 - Docker containers and microservices
- 201 - Amazon Elastic Container Service (ECS)
- 202 - Hands-on learning - Launch Docker containers on AWS Fargate
- 203 - Docker containers with SageMaker
- 204 - SageMaker MLOps for Kubernetes and SageMaker projects
- 205 - CI CD overview
- 206 - GitFlow, GitHub Flow
- 207 - (CI CD) Pipelines using AWS CodePipeline, CodeBuild, and CodeDeploy
- 208 - Automated tests in CI CD pipelines
- 209 - Services to automate orchestration in ML
- 210 - Hands-on learning - CI CD for training and deployment
- 211 - Model retraining framework
- 212 - Exam cram
9. Foundation Models and Applications
- 213 - Intro - Foundation models and applications
- 214 - Foundation model lifecycle
- 215 - Selection criteria for pre-trained models
- 216 - Tweaking inference parameters
- 217 - Hands-on learning - Tweaking inference parameters
- 218 - Embeddings and vector databases
- 219 - Retrieval augmented generation (RAG)
- 220 - RAG use cases
- 221 - RAG in Amazon Bedrock
- 222 - Hands-on learning - Amazon Bedrock knowledge bases
- 223 - Optimizing foundation models
- 224 - Choosing the right approach - Fine-tuning vs. RAG
- 225 - Fine-tuning a foundation model (deep dive)
- 226 - Data preparation for fine-tuning
- 227 - Evaluating a foundation model
- 228 - Foundation model performance metrics
- 229 - Business objectives for foundation models
10. AWS GenAI services and infrastructure
- 230 - Intro - GenAI services and infrastructure
- 231 - AWS services for GenAI
- 232 - Choosing foundation models and AWS GenAI service
- 233 - Why AWS services for GenAI
- 234 - EC2 for GenAI
- 235 - Why AWS infrastructure for GenAI
- 236 - Cost tradeoffs of AWS GenAI services
11. Monitoring and Optimization
- 237 - Intro - Monitoring and optimization
- 238 - ML Lens for monitoring
- 239 - CloudWatch for ML
- 240 - AWS X-Ray
- 241 - Amazon QuickSight
- 242 - Hands-on learning - Create an analysis using QuickSight
- 243 - AWS CloudTrail for ML
- 244 - SageMaker monitoring
- 245 - Regulatory compliance standards for AI systems
- 246 - AWS services for regulatory compliance
- 247 - Exam cram