Full Stack Machine Learning in AWS

Many AI and machine learning courses cover theoretical techniques of algorithms. In this course, we will train you to become a full stack machine learning engineer, capable of not just training models but also deploying and managing them in production.
You will learn full stack machine learning skills by building production machine learning microservices in AWS and a custom project that you can showcase to employers and peers.
This course has 8 hands on sessions where you will build, step by step, production grade machine learning services for business applications. You will learn how to build production AI in AWS, how to integrate it with an application, and how to manage an AI through its lifecycle.
You will also work with your peer students as a team on group project. and add the project to your own github portfolio.

Students who take this course will be able to:

  • Identify and frame business use cases that can be solved by AI and machine learning
  • Choose the right techniques, tools, frameworks to the business use cases
  • Build production AI on AWS, and manage through their lifecycle.
  • Hands on implementation of end to end AI for each use cases
    • Session 1: May 11, 5:30pm-7:00pm PST (US Pacific Time)
    • Session 2: May 13, 5:30pm-7:00pm PST
    • Session 3: May 18, 5:30pm-7:00pm PST
    • Session 4: May 20, 5:30pm-7:00pm PST
    • Session 5: May 25, 5:30pm-7:00pm PST
    • Session 6: May 27, 5:30pm-7:00pm PST
    • Session 7: June 1, 5:30pm-7:00pm PST
    • Session 8: June 3, 5:30pm-7:00pm PST

    • 4 weeks / 8 sessions / 12 hours
    • 8 lectures / 8 hands-on projects
    • Capstone project, Github portfolio
    • Live Sessions, Real time interaction
    • Slack support after class and homeworks
    • Watch replay anywhere any time

    Check the content tab for full course outlines.

    Developers, data scientists, students.

  • Basic familiarity with machine learning
  • AWS account (Free to sign up)
  • No coding prerequisite. We will provide self paced exercises where attendees, if interested, can code in Python, Java or Javascript.
    It is refundable upon request before the first session ends (before May 11th 8pm PST). 5% transaction fee is non-refundable.

    If you miss the live session or want to learn again, you can watch recorded sessions any time, along with interactive learning tools, slides, course materials

  • Earn Certificate of Completion
  • Job referral service is available, contact us for details
  • Scholarship is available, contact us for details
  • This course includes 8 hands on workshops, and each workshop will cover:
  • A business use case and how AI maps to that use case
  • An AI algorithm and AI internals technical topic. For example, how and when to use Regression, Classification and how to map the right powerful AI algorithms for each data type.
  • How to build a production AI (Feature Engineering, Model Training, Model Validation, Endpoints, Gateway/Lambda Integration, Application Integration).
  • One or more AWS tools. Across the 8 sessions we will cover AWS Sagemaker, AWS Sagemaker BuiltIn Algorithms, AWS Sagemaker with Custom Docker Containers, AWS Sagemaker Endpoint, AWS Lambda, AWS API Gateway, AWS Roles and Authentication, AWS Cloudwatch, AWS S3, Postman API testing, cURL, Production AI Best Practices. Microservice design pattern for AI deployment. We will also cover Navigator, a life cycle overlay tool that makes AWS tools easier to configure and use.
  • You will build 7 working production AI services.

  • We will cover the following business use cases:
  • Churn: Detect whether your customers are about leave your business or your product. Predict which customers are at risk of churn.
  • Pricing Analysis: Understand what factors most affect price. Predict how price can change with features. Assess viability of price for future products
  • Customer approvals: Should you approve a loan for a particular customer? Predict whether a customer is likely to be delinquent on a bill?
  • Appointment planning: Is a customer likely to miss an appointment? Can you plan your appointment schedule more effectively?
  • Removing bias in Business Analysis: Bias in your AI data can lead to poor outcomes, unhappy users or even legal problems. How to detect and remove sources of bias?
  • Sentiment Analysis: Are you customer’s happy with your product? What do their comments, tweets and other writings say about their feelings?
  • Making recommendations: What can you learn about your customers or users? Can you analyze their usage and see what else you can upsell to some users?

  • You will learn how to use these Production AI Cloud Tools:
  • How to configure and use S3 for your data
  • How to feature engineer your data with Python code
  • How to configure and use AWS Sagemaker. Deep dive on built in AWS Sagemaker algorithms KNN and XGBoost. How to hyper-parameter tune Sagemaker algorithms.
  • How to bring custom code into AWS Sagemaker as a Docker container
  • Configuring and using a Sagemaker Endpoint.
  • Connecting a Sagemaker Endpoint to a public URL via AWS Gateway and Lambda.
  • Integrating REST microservices with applications. Using CURL/Postman for API testing.
  • Cloud AWS best practices. Cloudwatch for logs, managing endpoints.
  • Navigator for ease of use. How to use Navigator and AWS together.

  • AI Algorithms, Algorithm Internals and ML Technical Concepts
  • How to build and use production grade AI. How to select an algorithm for a use case, train, deploy and use it in production, and measure how well it is doing.
  • How to map each use case to AI - what type of AI can be used, for what data type. How to measure the AI.
  • Powerful general purpose algorithms like XGBoost, LinearLearner, KNN, etc. and how they work internally and how to hyper-parameter tune them for best performance.
  • Metrics and practices for algorithmic evaluation and how to map them to use case.
  • AI Trust, Fairness and Bias. Managing AI related risk in business use case.
  • Explainability
  • An intro to advanced aspects of Production AI - live monitoring and diagnosis, model versioning, retraining and others.
  • Module 1: Build and run a production AI in the cloud. Case study - Customer Churn
    In this first session, we will show the steps needed to build and run a production AI in the cloud. We will illustrate these steps with our first business use case, Customer Churn. In the code lab, the attendees will build and test their own AI for customer churn using provided sample data.
    What attendees will learn:
    • Overview of the production AI lifecycle and all of its steps. How to go from data to running production AI
    • Description of cloud services that can be used for each stage
    • Overview of a customer churn problem and how to build an AI for it with AWS with Binary Classification Algorithms
    • Lab 1: Build an AI on AWS for Customer Churn and test the AI. All models and artifiacts will be in the attendee’s AWS account for their further use.

    Module 2: Evaluating the effectiveness of a production AI. Case study - Pricing Analysis
    This session session builds upon the first. We examine the use case of Pricing Analysis and how a production AI based on Regression techniques can address this use case. We follow the lifecycle steps shown in the first session, but delve into more depth on how to evaluate the effectiveness of the production AI. In the code lab, attendees will build and test their own AI on AWS for Pricing Analysis using publicly available datasets.
    What the attendees will learn:
    • How to build and evaluate production AIs that use Regression algorithms
    • Overview of a business Pricing Problem and how to build an AI for it using four powerful Regression Algorithms (LInear Learner, XGBoost, KNN and Factorization Machines)
    • How to bring in data from other sources (like Excel).
    • Common approaches to Feature Engineering - One Hot Encoding and Missing Value handling.
    • Lab 2: Build an AI on AWS for Pricing Analysis and test the AI. All models and artifacts will be in the attendee’s AWS account for their further use

    Module 3: Building and Hyper-Parameter Tuning a Production AI. Case Study of Credit Approvals
    In this session, we show how to hyper parameter tune AI algorithms trained in the cloud, and how to retrain and optimize production AI services. Using an example algorithm, K Nearest Neighbours, we show how this algorithm can be used to build a production AI, and also tuned for optimal performance and retrained in production. As a case study, we show how the business use case - Credit Approvals, can be built using the technical methods described here and the AI lifecycle steps. In the code lab, attendees will build and tune their own AI in AWs for Credit Approvals.
    What the attendees will learn:
    • How to build and hyper-parameter tune KNN for Binary Classification in the cloud
    • Overview of the Credit Approvals business use case, and how to build a production AI to solve this problem
    • How hyper-parameters affect solution quality and performance
    • How to retrain a production AI with new information and how to iteratively deploy increasingly accurate models
    • How to bring multiple datasets to bear for the same production AI, optimizing over time
    • Lab 3: Attendees will build a production AI for Credit Approvals using publicly available datasets. They will also iteratively tune and upgrade this AI in production

    Module 4: Test and Evaluate the Quality of a Production AI. Case study - Customer Appointment Planning
    In this session, we will focus on methods to test and evaluate the quality of production AIs. In particular, we delve into evaluation metrics beyond accuracy and cover both ML metrics (such as Confusion Matrix) and production service metrics (such as latency and scale) that are important for production. This session will focus on the application integration of production AI and how to test and evaluate this integration. We will also present a business use case - Customer Appointment Planning (how can you tell if a customer is going to keep their appointment) and will leverage this use case to illustrate the methods covered in this session. In the code lab, attendees will build an AI for this use case and can run the test experiments.
    What the attendees will learn:
    • How to evaluate a production AI with both ML metrics (like Accuracy, Confusion Matrix, True/False Positive/Negative etc.) and code metrics (throughput, accuracy, etc.)
    • How to test their AI service using CURL and Postman
    • How to integrate their AI service into Python, Java or Javascript applications
    • Lab 4: Attendees will build an AI for Customer Appointment planning and integrate it with an application code module in the language of their choice

    Module 5: Bias in AI. How to Detect and Remove in Production AI
    In this session, we focus on the critical issue of AI Bias. We cover the common ways that Bias can enter a production AI implementation and how to detect and remove Bias. As a case study, we use the publicly available COMPAS dataset. In the code lab, attendees will build two AIs using this dataset. The first will demonstrate bias and in the second, the attendees will test the effectiveness of various feature engineering approaches to reducing the bias.
    What the attendees will learn:
    • What is AI Bias and why should it be avoided?
    • How can AI Bias enter? How can it be detected and removed?
    • How to test for Bias and apply Feature Engineering to reduce it.
    • Lab 5: Attendees will build an AI with an open source dataset and test for Bias.

    Module 6: Building a production AI for Text Data. Case study of Sentiment Analysis
    This session focuses on Text Data. Building upon the first two sessions, we follow the same steps in production AI lifecycle but focus on Text Data and methods for Sentiment Analysis. We introduce the Sentiment Analysis use case and describe how AI can be used for this purpose. We dive deep into algorithms for Text Classification, particularly the Bag of Words approach, its operation, advantages and limitations. In the code lab, the attendees will build and test their own AI for Sentiment Analysis using Binary and Multiclass Text Classification, using two publicly available data sets.
    What the attendees will learn:
    • How to build and evaluate production AIs that use Text Classification algorithms
    • Overview of a business Sentiment Analysis problem and how to build an AI for it using Text Classification in either Binary or Multiclass form
    • How to bring in data from other sources (like Excel) and analyze social media feeds (Code lab will use Twitter feeds).
    • Lab 6: Build an AI on AWS for Pricing Analysis and test the AI. All models and artifacts will be in the attendee’s AWS account for their further use

    Module 7: Mapping AI problems to Techniques: Case Study - Making Recommendations
    In the first 6 sessions, we have covered different types of use cases, how to map AI to each use case, and different aspects of production AI (hyper parameter tuning, REST API test and integration, etc.) In this session we combine these into a methodology for mapping problems to AI methods for numerical, categorical and free form text data. We cover in depth a second powerful general purpose AI algorithm - XGBoost, and its hyper parameter tuning. In the code lab, attendees will build a production recommendation system using publicly available data, illustrating the concepts covered so far.
    What the attendees will learn:
    • A methodology for mapping use cases (with different data types) into AI algorithms and lifecycle steps
    • Internals and hyper parameter tuning for production XGBoost in the cloud
    • Introduction to recommendation use cases, and sample data sets.
    • Lab 7: Attendees will build and use a production AI for recommendations. Artifacts (trained models etc.) will be available in the attendee’s own AWS account for their continued use

    Module 8: Advanced topics in Production Cloud AI, Complete and showcase your project
    We will provide an overview of advanced topics that attendees can explore beyond this webinar series. These include Model Versioning, interactions between application versioning and model versioning, diagnostics of production AI in the presence of data changes, A/B testing, and others. In the code lab, students will complete their custom project and create a github and project repository to showcase their project. They can also create a project video if they choose to and put it in a hosting facility that we will provide..
    What attendees will learn:
    • Best practices for Production AI (model versioning, model integrity, retraining cycles, microservice API management and versioning). How to manage production application changes and production AI upgrades in concert.
    • Best practices for Cloud AI (debugging, instances, your cloud bill :-)).
    • Lab 8: Finish custom project
    Nisha Talagala

    founder of Pyxeda AI. Previously, Nisha co-founded ParallelM which pioneered the MLOps practice of managing machine learning in production. Nisha is a recognized leader in the operational machine learning space. Nisha was previously a Fellow at SanDisk and Fellow/Lead Architect at Fusion-io, where she worked on innovation in non-volatile memory technologies and applications.
    • Start Date: ended
    • Venue: Online
    • Fee:
      $299 $299 USD
    • Students enrolled:43
    • Status: course ended
    • Course Preview:

    • Any questions? Contact Us