Pluralsight review – AWS Certified Machine Learning Specialty
Contains affiliate links. If you go to Pluralsight’s website and make a purchase I may receive a small payment. The purchase price to you will be unchanged. Thank you for your support.
The AWS Certified Machine Learning Specialty learning path from Pluralsight has six high quality video courses taught by expert instructors. Two are introductory courses and the others correspond to the four knowledge domains of the certification syllabus or specification. There are over thirteen hours of video lectures. To use these courses you can sign up for a monthly subscription. Pluralsight also offers a great free trial so you can be confident of getting the course you need to pass the exam.
Course contents
- Demystifying the AWS Certified Machine Learning Specialty Exam
- Fundamentals of Machine Learning on AWS
- Data Engineering with AWS Machine Learning
- Exploratory Data Analysis with AWS Machine Learning
- Modeling with AWS Machine Learning
- Implementing and Operating AWS Machine Learning Solutions
Demystifying the AWS Certified Machine Learning Specialty Exam
This introductory video course is 1.26 hours long. It is divided into sections that review each of the four knowledge domains of the exam. Each section starts with a review of the core concepts and then poses some scenario based questions followed by answers.
Demystifying video course contents
- Course overview
- Understanding the exam
- Data engineering review
- Exploratory data analysis review
- Data modeling review
- Machine Learning operations review
Fundamentals of Machine Learning on AWS
Pluralsight course information for the Fundamentals of Machine Learning on AWS
This video course by Amber Isrealsen is 2.18 hours long. It covers the entire breadth of the Machine Learning certification course, but does not go into too much depth. This video course is a great way to get an overview without getting bogged down in the details. The video course is presented short videos organised into eight sections:
- Course intro
- Identifying opportunities for Machine Learning
- Defining Machine Learning problems
- Fetching and preparing data
- Training and Evaluating the Model
- The AWS Machine Learning stack
Amber recommends working along with the demo using an AWS account and Jupyter Notebooks with SageMaker Studio. There is a demo that takes you through the set up. The four demos are the highlights of the course:
- Environment set up
- Fetching and preparing data in SM Studio
- Training and evaluating the model in SageMaker Studio
- Monitoring the model
Amber’s course covers Machine Learning in AWS and shows the practical application of many Machine Learning features, services and concepts. Her treatment of problem framing, data preparation and Feature Engineering was good as well as when to use or not use Machine Learning and when to use supervised, unsupervised and reinforcement learning paradigms.
Data Engineering with AWS Machine Learning
Pluralsight course information for Data Engineering with AWS Machine Learning
This Data Engineering video course is 2.55 hours long. The instructor is Kim Schmidt. The course corresponds to the Data Engineering knowledge domain.
- Course overview
- Important data Characteristics to consider in a ML solution
- Typical data flows for ML
- Data storage options for ML
- Database options for ML
- Using a Data Warehouse or a Datalake for ML
- Streaming data ingestion solutions
- Batch data ingestion solutions
- Data transformation overview
- Data driven workflows using AWS Data Pipeline
- Data transformation using Apache Spark for ML
- Data transformation using serverless AWS Glue
The course starts by describing data characteristics and data flows in an organisation and the AWS services it uses. The data storage options for ML described are S3, EFS and EBS. S3 is described in detail with demos.The database options are RDS, Amazon Aurora, DynamoDB, DocumentDB. DynamoDB is described in detail. Data lakes and data warehouses are discussed and compared and Redshift is introduced.
Data transformation using Apache Spark and AWS Glue are described in detail aws well as AWS Glue Data catalogue and Athena. There is a good comparison of data types and structures including the advantages of Parquet format. All four members of the Kinesis family of services for streaming data are described and compared.
Exploratory Data Analysis with AWS Machine Learning
Pluralsight course information for Exploratory Data Analysis with AWS Machine Learning
The Exploratory Data Analysis course by Mohammed Osman is 2.16 hours long. This course is aligned with the Exploratory Data Analysis knowledge domain of the AWS certified Machine Learning Specialty exam.
- Course overview
- Machine Learning with AWS
- Data Analysis using AWS
- Data Visualization using AWS
- Data preparation using AWS
Modeling with AWS Machine Learning
Pluralsight course information for Modeling with AWS Machine Learning
The Machine Learning Modeling course by Saravanan Dhandapani is 2.13 hours long. This video course is aligned with the Modeling knowledge domain.
- Course overview
- ML foundation and supervised learning algorithms
- Deep Learning foundation and algorithms
- Train ML models
- Evaluate ML models
- Tune ML models
Implementing and Operating AWS Machine Learning Solutions
Pluralsight course information for Implementing and Operating AWS Machine Learning Solutions
This video course is 1.57 hours long. The course instructor is David Tucker. This course corresponds to the Machine Learning Implementation and Operations knowledge domain of the exam.
- Course overview
- AWS Machine Learning Services
- Deploying a SageMaker model
- Securing a SageMaker Implementation
- Implementing a highly-available ML solution
