CertNote/ Commute Study Notes
Roadmap
KOEN
CLF-C02 · FoundationalCloud Practitioner - Foundational
DVA-C02 · AssociateDeveloper - Associate
SAA-C03 · AssociateSolutions Architect - Associate
SOA-C02 · AssociateCloudOps Engineer - Associate
SAP-C02 · ProfessionalSolutions Architect - Professional
DOP-C02 · ProfessionalDevOps Engineer - Professional
Linux Master 2 · 2급KAIT Linux Master - Level 2
SCS-C03 · SpecialtySecurity - Specialty
Linux Master 1 · 1급KAIT Linux Master - Level 1
MLA-C01 · AssociateMachine Learning Engineer - Associate
AIF-C01 · FoundationalAI Practitioner - Foundational
DEA-C01 · AssociateData Engineer - Associate
MLS-C01 · SpecialtyMachine Learning - Specialty
  • Week 1
    • 1.The ML Lifecycle (from a Specialty Perspective)
    • 2.Data Storage for ML: S3, EFS, FSx for Lustre, and Data Formats
    • 3.Data Ingestion: Kinesis, Glue, Batch vs. Streaming
    • 4.Data Labeling: SageMaker Ground Truth, Active Learning, Label Quality
    • 5.Week 1 Comprehensive Review: ML Overview & Data Engineering 1
  • Week 2
  • Week 3
  • Week 4
  • Week 5
  • Week 6
  • Week 7
  • Week 8
  • Week 9
  • Week 10
  • Week 11
  • Week 12
SQLD · 개발자SQL Developer (SQLD)

© CertNote · 주간랩스

  • About
  • Changelog
  • Contact
  • Terms
  • Privacy
← All certifications/MLS-C01

Machine Learning - Specialty

12 weeks · 60 days · Specialty

Start with Week 1

Read MLS-C01 pass reviews →

Exam Information

Specialty · Hands-on experience in the domain recommended
Questions
65
Duration
180min
Passing
750 / 1000
Cost
$300
Validity
3y

Domain Weights

Data Engineering20%
Exploratory Data Analysis24%
Modeling36%
Machine Learning Implementation and Operations20%
FormatMultiple choice and multiple response
PrerequisitesNone (recommended: 2+ years of experience developing and running ML/deep learning workloads)
LanguagesEnglish, Korean, Japanese, Simplified Chinese

Benefits & Tips

  • Passing earns you a 50% discount voucher for your next exam. Find it under "Benefits" in your AWS Certification account and use it for recertification or another certification (it has an expiry date, so use it before then).
  • The certification is valid for 3 years and must be renewed before it expires. You can use the 50% voucher for recertification too.
  • There is no free retake (every attempt is paid in full). Passing on the first try is the cheapest route, so take the real exam once your mock exam scores clear the passing mark.
  • Passing also earns you a Credly digital badge that you can add to LinkedIn and your email signature.

FAQ

How many questions are on the MLS-C01 exam, and how long is it?+

MLS-C01 has 65 questions and a time limit of 180 minutes. Questions are multiple choice and multiple response.

What is the passing score?+

You need 750 or higher out of 1000 to pass. The score is a scaled score adjusted for question difficulty, so it is not the same as a simple percentage of correct answers.

How much does the exam cost and how do I register?+

The exam fee is $300 USD, and you can take it through Pearson VUE at a test center or as an online proctored exam. There is no free retake, so you pay the full fee each time you sit the exam.

How long is the certification valid? How do I recertify?+

The certification is valid for 3 years after you pass, and you must recertify before it expires. When you pass, you receive a 50% discount voucher for your next exam, which you can use for recertification or for another AWS certification exam.

Can I take the exam in Korean?+

Yes, it is offered in 4 languages in total, including Korean. You can choose your language when you register for the exam.

Official Exam Guide Register for Exam

Week 1

  • Day 1The ML Lifecycle (from a Specialty Perspective)
  • Day 2Data Storage for ML: S3, EFS, FSx for Lustre, and Data Formats
  • Day 3Data Ingestion: Kinesis, Glue, Batch vs. Streaming
  • Day 4Data Labeling: SageMaker Ground Truth, Active Learning, Label Quality
  • Day 5Week 1 Comprehensive Review: ML Overview & Data Engineering 1

Week 2

  • Day 1Data Transformation and ETL: AWS Glue, Spark, and EMR
  • Day 2Automating ML Training Pipelines: Step Functions and SageMaker Pipelines
  • Day 3Data Augmentation and Synthesis: Handling Scarce and Imbalanced Data
  • Day 4Optimizing Training Data Storage and Access: Pipe Mode vs File Mode, FSx for Lustre, and Distributed Training
  • Day 5Week 2 Comprehensive Review: From Transformation to Distributed Training Data Supply

Week 3

  • Day 1Data Cleaning: Missing Values, Outlier Detection, Duplicates and Errors
  • Day 2Feature Engineering: Scaling, Encoding, and Binning
  • Day 3Time Series, Text Features, and High-Cardinality Categorical Handling
  • Day 4SageMaker Tools: Data Wrangler, Processing Job, Feature Store
  • Day 5Week 3 Comprehensive Review: Cleaning and Feature Engineering

Week 4

  • Day 1Dimensionality Reduction: PCA, t-SNE, and the Curse of Dimensionality
  • Day 2Feature Selection: Filter, Wrapper and Embedded Methods, Importance, and Multicollinearity
  • Day 3Data Visualization: Distributions, Correlations, QuickSight, and Drawing Insights
  • Day 4Handling Class Imbalance: Oversampling, Undersampling, SMOTE, Class Weights, Evaluation
  • Day 5Week 4 Comprehensive Review: Dimensionality, Feature Selection, Visualization, Imbalance

Week 5

  • Day 1Statistics Basics: Distributions, Central Tendency, Spread, Transformations, and Sample vs Population
  • Day 2Correlation and Relationships: Correlation Coefficients, Causation vs. Correlation, Multivariate Relationships
  • Day 3Data Leakage: Causes, Detection, Prevention, and Time-Series and Target Leakage
  • Day 4Validation Design: Train/Validation/Test Splits, Cross-Validation, Time-Series Splits, Stratified Sampling
  • Day 5Week 5 Comprehensive Review: Statistics and Validation Design

Week 6

  • Day 1Algorithm Selection: Mapping by Problem Type
  • Day 2SageMaker Builtin 1: XGBoost, Linear Learner, K-Means, KNN
  • Day 3SageMaker Builtin 2: Text, Images, Time Series, Recommendations
  • Day 4Unsupervised Learning and Anomaly Detection: RCF, PCA, IP Insights, Topic Models (LDA/NTM)
  • Day 5Week 6 Comprehensive Review: Algorithm Selection and SageMaker Builtin Algorithms

Week 7

  • Day 1Neural Network Basics: From the Perceptron to Backpropagation
  • Day 2CNN: Convolutional Neural Networks and Computer Vision
  • Day 3RNNs and Sequence Models: From LSTM to Transformer
  • Day 4Training Techniques and Transfer Learning
  • Day 5Week 7 Synthesis: Deep Learning Summary

Week 8

  • Day 1SageMaker Training Jobs: Estimator, Input Modes, Distributed Training, Spot
  • Day 2Hyperparameter Tuning (AMT): Bayesian, Random, Hyperband
  • Day 3Overfitting/Underfitting: Diagnosis and Regularization/Data Augmentation
  • Day 4Learning Optimization: Batch Size, Learning Rate, Gradient Issues, Debugger/Profiler
  • Day 5Week 8 Comprehensive Review: Training, Tuning, Generalization

Week 9

  • Day 1Classification Evaluation Metrics: Accuracy, Precision, Recall, F1, and the Confusion Matrix
  • Day 2ROC/AUC and Threshold Tuning: Reading Model Performance from Curves
  • Day 3Regression Evaluation Metrics: RMSE, MAE, MAPE, R², and Residual Analysis
  • Day 4Model Debugging and Bias: SageMaker Debugger and Clarify
  • Day 5Week 9 Comprehensive Review: Evaluation and Debugging

Week 10

  • Day 1Inference Options: Real-time vs Serverless vs Asynchronous vs Batch Transform
  • Day 2Operating Real-Time Endpoints: Configuration, Auto Scaling, and Multi-Model Endpoints
  • Day 3Inference Optimization: SageMaker Neo, Elastic Inference, Inferentia, and Inference Pipelines
  • Day 4Model Deployment Strategies: A/B Testing, Blue/Green, Canary, Shadow, Rollback
  • Day 5Week 10 Comprehensive Review: ML Implementation and Operations 1 — Deployment and Inference

Week 11

  • Day 1Model Monitoring: SageMaker Model Monitor and Drift Response
  • Day 2MLOps: SageMaker Pipelines, Model Registry, CI/CD
  • Day 3ML Security: IAM Execution Roles, VPC Isolation, KMS Encryption
  • Day 4Operations & Cost: Cost Optimization, Logging/Audit, Disaster Recovery
  • Day 5Week 11 Comprehensive Review: Monitoring, MLOps, Security, Operations

Week 12

  • Day 1Domains 1 & 2 Integration: Data Engineering + EDA
  • Day 2Domain 3 Integration: Modeling (Algorithm to Evaluation)
  • Day 3Domain 4 Integration: ML Implementation & Operations
  • Day 4Synthesis: 4 Domains + End-to-End Scenarios
  • Day 5D-Day Wrap-Up: Exam Structure, Time Allocation, Requirement Translation Tables, Trap Roundup