DEV Community πŸ‘©β€πŸ’»πŸ‘¨β€πŸ’»

Cover image for Study Plan to pass exam AWS Machine Learning Specialty exam with tips and advice
Marwa Talaat for AWS Community Builders

Posted on

Study Plan to pass exam AWS Machine Learning Specialty exam with tips and advice

The AWS Machine Learning Specialty exam is a challenging task that requires a lot of commitment, dedication, and covering theory and practice. The main objective of the exam is to validate your expertise in machine learning and your ability to apply it in the AWS cloud. It requires a lot of knowledge and experience to pass.

Whether or Not You Should followΒ This Guide?

Before we get started, let's evaluate if this tutorial is right for you. The target audience for this learning guide is:

  • Understand at least one high-level programming language in-depth and practical development experience (at least 2 years as recommended by AWS)
  • Basic understanding of Machine Learning. if you have a solid knowledge of data science and machine learning. You won’t need to go through all these resources.
  • You have 3 hours a day, 5 times a week excluding weekends πŸ˜ƒ

These learning resources are offered based on the real requirement in each plan stage.

Stage one: Testing the waters:

Learning Resource Duration Outcomes
What is AWS Cloud? 60 minutes You will learn about the foundations of getting started in the AWS Cloud.
AWS Cloud Practitioner Essentials 6 hours This course is intended for anyone who, regardless of their technical positions, wants a general grasp of the Amazon Web Services (AWS) Cloud. You will gain an understanding of AWS Cloud principles, AWS services, security, architecture, pricing, and support. You may use this course to be prepared for the AWS Certified Cloud Practitioner test as well.
Demystifying AI/ML/DL 45 minutes You will learn the relationship between artificial intelligence (AI), machine learning (ML), and deep learning after completing this collection of courses (DL).
AWS Foundations: Machine Learning Basics 30 minutes You learn about the concepts, terminology, and processes of the exciting topic of machine learning!
Learn Python on AWS Workshop 3 Hours You will learn the fundamentals of Python programming in this class utilizing Amazon Web Services (AWS).It is intended for beginners who have never coded in Python before, and it employs similar ways of introducing the fundamentals as previous books and tutorials on the Python programming language.

Stage Two: Self-based Learning Resources

These learning resources are crucial components of the suggested learning strategy and will aid in your acquisition of new AWS machine learning capabilities and services.

Week- 1: Average 11 hours to 13 hours

During this week you get to know the fundamentals of AWS cloud and AWS machine learning.

Learning Resource Duration Outcomes
What is Cloud Computing with AWS? 10 minutes You will get an overview of the AWS cloud, functionalities, regions, etc.
AWS glossary 30 minutes AWS Glossary to know definitions of key terms and concepts
Job Roles in the Cloud 30 minutes You will learn about the typical job roles applicable to an enterprise-level AWS Cloud environment
AWS Pricing 15 minutes You will learn a broad view of How does AWS pricing work? How do you pay for AWS? And pricing for AWS products
How AWS Pricing Works: AWS Pricing Overview 60 minutes You'll discover that the flexibility to adjust expenses to match your needs, even as those needs change over time, is one of the key advantages of cloud services
AWS Support Plans 10 minutes You will discover how AWS Support plans are created to provide you with the ideal combination of tools and access to knowledge so that you can succeed with AWS while maximizing performance, minimizing risk, and keeping costs in check.
15 minutes You will get the AWS Shared Responsibility Model introduction. This course clarifies the separation of those obligations between AWS and the client, who both share responsibility for security and compliance.
AWS Cloud Security 5 minutes You will discover how AWS enables you to take back control of your organization and instils the confidence you need to operate it safely in the most adaptable and secure cloud computing environment currently available.
Machine Learning for Leaders 70 minutes This course will teach you how as a business leader, machine learning may help your teams in maximizing project performance and gaining crucial insight into your company's or your customers' demands.
Machine Learning for Business Challenges 60 minutes You will learn how can you use machine learning (ML) to address business challenges in ways that weren't previously feasible, but you must think broadly.
Machine Learning Terminology and Process 60 minutes You will understand the fundamentals of machine learning in this course, as well as how machines analyze data. We thoroughly examine each stage of the machine learning process and define some of the words and methods that are frequently used in a particular stage of an ML project.
Process Model: CRISP-DM on the AWS Stack 50 minutes You learn about data science as a circular process through the CRISP-DM paradigm. With the help of Jake Chen, an AWS data scientist consultant, we'll go over the CRISP-DM methodology and framework before putting its six stages to use in your day-to-day job as a data scientist.
Machine Learning on AWS 30 minutes You will get an overview of the machine learning capabilities that AWS has.
Exploring the Machine Learning Toolset 20 minutes You will learn that anyone can apply machine learning no matter what your background or experience is. you'll go through a few of the AWS machine learning services you can use to create models and give app intelligence in this lecture.
Data Analytics Fundamentals 210 minutes You will learn about the process of planning data analysis solutions, as well as the numerous data analytic techniques involved.

Week- 2: Average 16 hours to 19 hours

This week is kind of tough you will go back to basics in math to understand vectors and matrices, linear algebra, probability theorems, univariate calculus, and multivariate calculus as well as elements of data science.

Learning Resource Duration Outcomes
Math for Machine Learning 480 minutes Modern machine learning requires an understanding of vectors and matrices, linear algebra, probability theorems, univariate calculus, and multivariate calculus.
The Elements of Data Science 480 minutes You will learn how to develop and constantly improve machine learning models.

Week- 3: Average 15 hours to 17 hours

Concepts and best practices for AWS Machine Learning in the cloud.

Learning Resource Duration Outcomes
Planning a Machine Learning Project 30 minutes You learn how to assess the data, time, and production requirements for a successful ML project.
Building a Machine Learning Ready Organization 30 minutes This course outlines the components required for successful machine learning adoption in organizations.
Introduction to Amazon SageMaker 13 minutes
AWS Foundations: How Amazon SageMaker Can Help 30 minutes You will explore how Amazon SageMaker mitigates the primary problems associated with creating a machine learning pipeline.
Developing Machine Learning Applications 240 minutes You'll look at Amazon SageMaker, a fully managed machine learning platform. We'll talk about how to train and fine-tune models; how certain algorithms are built-in, etc.
Amazon SageMaker: Build an Object Detection Model Using Images Labeled with Ground Truth 70 minutes You will learn how to implement a machine learning pipeline using Amazon SageMaker and Amazon SageMaker Ground Truth.
Machine Learning Security 120 minutes You will how to control and maintain permissions, as well as approve traffic, which are all part of developing highly secure applications and environments on the AWS platform.
Amazon SageMaker Technical Deep Dive Series 275 minutes Deep dive videos series provided by AWS.
Deep Learning on AWS 120 minutes A technical guide to running deep learning in AWS cloud.

Week- 4: Average 18 hours to 20 hours

Learning Resource Duration Outcomes
Analyze Datasets and Train ML Models using AutoML 18 hours Prepare data, detect statistical data biases, and perform feature engineering at scale to train models with pre-built algorithms.

Week- 5: Average 13 hours to 15 hours

Learning Resource Duration Outcomes
Build, Train, and Deploy ML Pipelines using BERT 13 hours
  • Store and manage machine learning features using a feature store.
  • Debug, profile, tune and evaluate models while tracking data lineage and model artifacts.

Week- 6: Average 14 hours to 16 hours

Learning Resource Duration Outcomes
Optimize ML Models and Deploy Human-in-the-Loop Pipelines 14 hours You will learn how to build, train, and deploy scalable, end-to-end ML pipelines - both automated and human-in-the-loop - in the AWS cloud.

Stage Three: Real live environment practice

Week- 7 & 8 & 9: Average 36 hours to 40 hours

It's time to get your hands dirty by solving some ML Use Cases of your own from AWS SageMaker Use Cases repo.

Learning Resource Duration Outcomes
Risk Bucketing 6 hours One of the most common use cases for machine learning in financial services is estimating the probability of default on a loan.
Churn Prediction for Music Streaming 6 hours Use case to detect whether the customer tends to leave and stop paying for a service.
Payment Classification 6 hours Use case to classify payment transactions.
Fleet Predictive Maintenance 6 hours Use case to demonstrate a Predictive Maintenance (PrM) solution for automible fleet maintenance via Amazon SageMaker Studio.
Amazon SageMaker Pipelines 6 hours In this use case we use SageMaker Pipelines to train and deploy a text classification model to predict e-commerce product ratings based on customers’ product reviews.
Computer Vision 6 hours Use case about computer Vision for Medical Imaging - Pipeline Mode

Stage Four: Prepare for and take the AWS Certified Machine Learning - Specialty certification exam

Additional recommended resources

Till this stage you should be about 50% ready for the exam. Though AWS provides an exact passing score of 750 for this test, it's safe to infer that a score of 75% to 80% is necessary to pass. With an extra month or two of preparation, I feel the certification is well within reach.

Official documentations are important preparation resource. Its always recommended to review the following:

These tips for exam preparation:

Last but not least, always remember that there is no need to know all the answers to ace the exam, so don't put yourself under unnecessary stress!

Best of luck with the exam!

Top comments (0)

12 APIs That You Will Love

>> Check out this classic DEV post <<