MLS-C01

Review material and practice exercises to prepare for the exam.
The content is intended as tool to remember the domains to be tested, thus, the notebooks contain short exercises useful to see some concepts (no AWS) in action and the notes explains the theoretical minimum (Yeah! I know I am not Leonard Susskind) in simple words of topics that are very complex and vast.

The material is organized in the 4 domains of the exam and one practical, which contains exercises using AWS services and applying ML common tools.

1. Data Engineering
2. Data Analysis
3. Modelling
4. Implementation
5. Practical exercises in AWS

Exam Content Outline

Domain 1: Data Engineering (20%)

1. Create data repositories for machine learning.
2. Identify and implement a data-ingestion solution.
3. Identify and implement a data-transformation solution.

Domain 2: Exploratory Data Analysis (24%)

1. Sanitize and prepare data for modeling.
2. Perform feature engineering.
3. Analyze and visualize data for machine learning.

Domain 3: Modeling (36%)

1. Frame business problems as machine learning problems.
2. Select the appropriate model(s) for a given machine learning problem.
3. Train machine learning models.
4. Perform hyperparameter optimization.
5. Evaluate machine learning models.

Domain 4: Machine Learning Implementation and Operations (20%)

1. Build machine learning solutions for performance, availability, scalability, resiliency, and fault tolerance.
2. Recommend and implement the appropriate machine learning services and features for a given problem.
3. Apply basic AWS security practices to machine learning solutions.

4. Deploy and operationalize machine learning solutions.

   For exams details, visit the official site here.