What students say...
"Having tried a number of machine learning courses I can wholeheartedly recommend Mike’s as the best."
- Adrian, Technical Innovations Manager, UK
"Mike’s course has everything you would want in a high-quality course." "Mike is very responsive to any questions you have and really wants his students to learn the material and not just pass the exam."
- Bill, Data/Cloud Engineer USA
Machine Learning and Deep Learning core concepts clearly explained.
Understanding core concepts is a foundation for mastering Machine Learning and Deep Learning.
This course starts at the very beginning with a clear explanation of these concepts and builds upon them without assuming any prior knowledge.
Learn the craft of Machine Learning through real understanding.
Practical examples with hands on experience.
Gain valuable experience and gain real-world skills for working in the industry.
Through many practical and hands-on lessons, code is provided to build real solutions. Follow the lesson, and then adapt the code and experiment.
Build your skillset through guided examples.
Designed for the AWS MLS-C01 exam.
Gain the confidence to pass the AWS Machine Learning Specialty Certification and announce your skills to the world.
This course is designed from scratch to help you pass the certification exam and provide useful knowledge if apply for ML Engineering jobs.
Connect with other students on the same journey and share your experience.
Course Curriculum
- My First Model (13:25)
- Problem Space (7:26)
- Machine Learning Life Cycle (6:27)
- Types of Machine Learning (11:03)
- Build: Machine Learning Environment - Part 1 (9:10)
- Build: Machine Learning Environment - Part 2 (11:09)
- Build: My First Model - Part 1 (12:40)
- Build: My First Model - Part 2 (11:27)
- Build: My First Model - Part 3 (10:05)
- Where to Find Data (10:03)
- Build: Loading Sample Data with scikit-learn “California Housing” (25:44)
- Build: Loading Sample Data with scikit-learn “MNIST hand-written digits” (11:43)
- Build: Create Sample Data with scikit-learn “Random regression problem.” (12:03)
- Build: Loading Data from S3 into a Notebook (10:21)
- Data Exploration: Useless Data (5:04)
- Data Exploration: Binary & Continuous (4:18)
- Data Exploration: Categorical (6:34)
- Data Exploration: Text & Temporal (3:35)
- Feature Encoding (9:42)
- Build: Feature Encoding in Jupyter (14:37)
- Text Encoding (7:44)
- Missing Data (8:28)
- Build: Imputation with Jupyter (14:44)
- Unbalanced Data (7:50)
- Feature Engineering (6:59)
- Updating the Machine Learning Environment (4:03)
- Logistic Regression (10:35)
- Build: Logistic Regression with scikit-learn (13:51)
- Linear Regression & Stochastic Gradient Descent (12:30)
- Build: Linear Regression (13:54)
- Build: Linear Regression & SGD (5:39)
- Support Vector Machines (10:54)
- Build: Support Vector Machines 1 (13:06)
- Build: Support Vector Machines 2 (12:55)
- Decision Trees Part 1 (12:22)
- Decision Trees Part 2 (10:57)
- Random Forests (7:19)
- Build: Random Forests (19:38)
- K-means Clustering (13:51)
- Build: K-means Clustering (12:17)
- K-Nearest Neighbours (3:17)
- Build: K-nearest Neighbors (7:07)
- Latent Dirichlet Allocation (LDA) (15:51)
- Mini Project: Latent Dirichlet Allocation (LDA) - Part 1 (9:45)
- Mini Project: Latent Dirichlet Allocation (LDA) - Part 2 (10:29)
- Mini Project: Latent Dirichlet Allocation (LDA) - Part 3 (6:25)
- Mini Project: Latent Dirichlet Allocation (LDA) - Part 4 (11:03)
- Principal Component Analysis (PCA) (12:11)
- Build: Principal Component Analysis (PCA) (9:48)
- Introduction to Neural Networks (12:46)
- Inside the Neuron (16:53)
- Training a Neural Network (19:47)
- Build: My First Neural Network - Part 1 (9:29)
- Build: My First Neural Network - Part 2 (13:33)
- Build: MNIST Handwritten Dataset (12:27)
- Matchbox Tic-Tac-Toe (11:22)
- CNN (Convolutional Neural Networks) Part 1 (16:28)
- CNN (Convolutional Neural Networks) Part 2 (10:44)
- Build: CNN Lego Sorting - Part 1 (14:27)
- Build: CNN Lego Sorting - Part 2 (18:27)
- RNN (Recurrent Neural Networks) (12:08)
- Build: RNN (Recurrent Neural Networks) (15:10)
- Word2vec (15:30)
- Demo: Word2vec with the (tiny) h2o dataset (6:33)
- Build: Word2vec - Part 1 (13:36)
- Build: Word2vec: Part 2 (12:30)
- Seq2seq (6:57)
- AI Services - Introduction (3:49)
- Amazon Lex and Polly (14:01)
- Amazon Textract and Comprehend (10:05)
- Amazon Transcribe and Translate (8:32)
- Amazon Rekognition (9:01)
- Amazon Forecast, Personalize & Fraud Detector (5:22)
- Build: Serverless AI Solution - Part 1 (8:54)
- Build: Serverless AI Solution - Part 2 (15:29)
- Build: Serverless AI Solution - Part 3 (12:54)
- SageMaker - Introduction (13:11)
- SageMaker - Console (10:18)
- Build: SageMaker Image Classificiation - Part 1 (16:30)
- Build: SageMaker Image Classificiation - Part 2 (8:42)
- Build: SageMaker Image Classificiation - Part 3 (15:25)
- Build: SageMaker Image Classificiation - Part 4 (14:10)
- Build: SageMaker Image Classificiation - Part 5 (7:06)
- Build: SageMaker Image Classificiation - Part 6 (20:58)
- Build: SageMaker SDK - Part 1 (15:13)
- Build: SageMaker SDK - Part 2 (10:12)
- SageMaker Logical View (11:59)
- SageMaker Notebooks (9:49)
- SageMaker Built-in Algorithms (21:05)
- Bonus: SageMaker Built-in Algorithms Quiz Tool (4:15)
- SageMaker Modes - Runnnig your own code (3:05)
- Build: SageMaker Script Mode - Part 1 (13:29)
- Build: SageMaker Script Mode - Part 2 (20:49)
- Build: SageMaker Script Mode - Part 3 (6:19)
- Build: SageMaker Script Mode - Part 4 (4:41)
- SageMaker Ground Truth (13:04)
- SageMaker Studio (16:24)
- S3 (Simple Storage Service) - Part 1 (8:18)
- S3 (Simple Storage Service) - Part 2 (8:32)
- EMR - Part 1 (8:49)
- EMR - Part 2 (10:01)
- Athena (2:42)
- Glue (11:15)
- Build: Glue, Athena and QuickSight - Part 1 (18:57)
- Build: Glue, Athena and QuickSight - Part 2 (11:55)
- Build: Glue, Athena and QuickSight - Part 3 (8:06)
- Build: Glue, Athena and QuickSight - Part 4 (19:10)
- Kinesis Streams (13:47)
- Kinesis Data Analytics (3:34)
- Kinesis Firehose (4:45)
- Build: Kinesis Streams, Analytics and Firehose - Part 1 (12:34)
- Build: Kinesis Streams, Analytics and Firehose - Part 2 (7:02)
- Build: Kinesis Streams, Analytics and Firehose - Part 3 (10:15)
- Build: Kinesis Streams, Analytics and Firehose - Part 4 (7:13)
- Build: Kinesis Streams, Analytics and Firehose - Clean-up (5:51)
- Kinesis Video Streams (5:22)
- AWS Batch (15:50)
- DMS (Database Migration Service) (9:29)
Frequently Asked Questions (FAQ):
Who can take this course?
While I welcome anyone who wants to take this course, you need to know that the MLS-C01 exam is not a typical entry-level certification. I recommend that you have passed, or could pass, and AWS associate-level certification before tackling this course.
However, if you're technically minded, you want to learn about machine learning, and you don't plan to take the certification for a while (or ever) then you should find this course useful to get started in ML.
What do I need to take the course?
Apart from time, and Internet access, etc, you will need an AWS account to be able to follow along with the build activities. I strongly recommend that you create a new account specifically for the purpose of studying any area of AWS, and this is no different.
I am new to AWS, can I take this course?
The first half of the course is not focused on AWS, but it's mentioned here and there. The second half of the course assumes that you have AWS knowledge, so please keep this in mind. If you want to learn AWS from scratch then here is an excellent course to consider, that starts from a position of no AWS experience: https://learn.cantrill.io/p/aws-certified-solutions-architect-associate-saa-c02
Is the price for a one-off purchase or monthly subscription?
One-off purchase.
Are those testimonials real?
Yep!
How can I contact Mike?
There are a few ways:
Connect via LinkedIn here: https://linkedin.com/in/mikegchambers
Via Twitter: @mikegchambers
Hi, I’m Mike
Hello! I was one of the first in the world to get AWS certified, and since then I have helped hundreds of thousands of people from all around the world to advance their career and get certified too.
As well as having a passion for teaching, I'm an experienced Solutions Architect working around the world with some of the largest companies on the planet, governments, and amazing start-ups.
Originally from the UK, I now live in sunny Queensland Australia with my amazing family, Sparky the dog, and Asher the cat (plus a transient collection of emergency fostered animals).