AWS Certified Machine Learning Specialty Exam Study Guide [MLS-C01]

You can access MLS-C01 Exam AWS official page here

Preparing for the AWS Certified Machine Learning Specialty exam? Don’t know where to start? This post is the AWS Certified Machine Learning Certificate Study Guide (with links to each objective in the exam domain).

I have curated a detailed list of articles from AWS documentation and other blogs for each objective of the AWS Certified Machine Learning (MLS-C01) exam. Please share the post within your circles so it helps them to prepare for the exam.

Skills Measured

Data Engineering – 20%
Exploratory Data Analysis – 24%
Modeling – 36%
Machine Learning Implementation and Operations – 20%

MLS-C01 Exam Free Study Guide

For each test objective, I’ve compiled a thorough collection of articles from Microsoft documentation. Please feel free to forward this page to your friends and coworkers in order to assist them in preparing for the test .

Data Engineering - 20%

Create Data Repositories for Machine Learning

Identify and Implement a Data-ingestion Solution

Identify and Implement a Data-transformation Solution

Exploratory Data Analysis - 24%

Sanitize and Prepare Data for Modeling

Perform Feature Engineering

Analyze and Visualize Data for Machine Learning

Analyzing data for Machine Learning
1. Analyzing Data with Amazon Machine Learning
2. Explore, Analyze & Process data
Visualizing data for Machine Learning
1. Visualizing the distribution of data
2. Visualizing insights for binary models
3. Visualizing insights for Regression models
4. Visualizing insights for Multi-class Models
5. Visualizing Results in Amazon SageMaker Studio
6. Visualize Model Analysis in Amazon SageMaker Studio

Modeling - 36%

Frame Business Problems as Machine Learning Problems

Select the Appropriate Model(s) for a Given Machine Learning Problem

Amazon Machine Learning: Types of ML Models
Excellent article on how to select an ML algorithm (although for Azure ML)
Review all the built-in algorithms in SageMaker to understand their applicability:
Supervised Learning Algorithms:
DeepAR forecasting (Forecasts time series using Neural Networks)
Factorization Machines (Captures interactions between features)
Image Classification Algorithm (Multi-label image classification)
K-Nearest Neighbors Algorithm (Predicts similar items by evaluating distance)
Linear Learner Algorithm (for Classification or Regression problems)
Object2Vec Algorithm (General-purpose algorithm)
Object Detection Algorithm (Classifies objects in images)
Sequence-to-Sequence Algorithm (for text summarization)
Unsupervised Learning Algorithms:
IP Insights Algorithm (Learns the usage patterns of IPv4 addresses)
K-Means (Finds discrete groups within data)
Latent Dirichlet Allocation (LDA) Algorithm (Unsupervised learning algorithm)
Neural Topic Model (NTM) Algorithm (organize a corpus of documents into topics)
Principal Component Analysis (PCA) Algorithm (for reducing the dimensionality)
Random Cut Forest (RCF) Algorithm (Detects anomalous data points in a data set)
Other Machine Learning Algorithms:
BlazingText Algorithm (Text Classification)
Semantic Segmentation Algorithm (tags every pixel in an image with a label)
XGBoost Algorithm

Train Machine Learning Models

Build, Train, and Deploy a Machine Learning Model with SageMaker
Train a Model with Amazon SageMaker
Incremental training of model in SageMaker
Training with Amazon EC2 Spot Instances
Other AWS documentation items to review:
Understanding the training process
Train a Deep Learning model

Perform Hyperparameter Optimization

Evaluate Machine Learning Models

Evaluating ML Models:
1. Binary Model Insights
2. Multiclass Model Insights
3. Regression Model Insights
Understand the Cross-validation technique for evaluating ML Models
Evaluating Model Fit: Underfitting vs. Overfitting
Evaluate Model Accuracy of the following:
1. Binary Classification
2. Multiclass Classification
3. Regression Models

Machine Learning Implementation and Operations - 20%

Build Machine Learning Solutions for Performance, Availability, Scalability, Resiliency, and Fault Tolerance

Performance:
1. Review the ML Model’s Predictive Performance
Availability:
1. Deploy Multiple Instances Across Availability Zones
Scalability:
1. Amazon SageMaker: Infinitely Scalable Machine Learning Algorithms
2. Review this Whitepaper: Power Machine Learning at Scale
3. Scaling Machine Learning from 0 to millions of users
Resiliency:
1. Resiliency in Amazon SageMaker
2. AWS’ approach to operational resilience

Recommend and Implement the Appropriate Machine Learning Services and Features for a Given Problem

Apply Basic AWS Security Practices to Machine Learning Solutions

Deploy and Operationalize Machine Learning Solutions

2 ways to deploy your model:
a. Amazon SageMaker hosting services (to set up an endpoint to get predictions)
Deploy a Model on Amazon SageMaker Hosting Services
Example: Deploying a Model to Amazon SageMaker Hosting Services
b. Amazon SageMaker batch transform (to get predictions on the entire dataset)
Overview: Deploying a model with Amazon SageMaker batch transform
Deploy the Model with Batch Transform
Review deployment best practices
Troubleshoot Amazon SageMaker Model Deployments

This brings us to the end of the AWS Certified Machine Learning – Specialty [MLS-C01] Exam Preparation Study Guide.