Build end to end AI applications - Online

You probably learned what is AI and machine learning, and learned how to train models/algorithms in Jupyter notebooks. But how will you integrate AI features into your products/services? This includes not only just training models, but also many engineering processes like deployment, serving models, maintaining models, scaling models, monitoring results,etc.. This course includes a series of hands-on workshops. Each workshop presents a business use case using AI technics to sovle
Students who take this course will be able to:
  • Identify and frame business use cases that can be solved by AI
  • Choose the right techniques, tools, frameworks to the business use cases
  • Build a production AI
  • Hands on implementation of an end to end AI for each use cases
    • Session 1: Oct.30th 10am-11:30am PST
    • Session 2: Nov.1st 10am-11:30am PST
    • Session 3: Nov.6th 10am-11:30am PST
    • Session 4: Nov.8th 10am-11:30am PST
    • Session 5: Nov.13th 10am-11:30am PST
    • Session 6: Nov.15th 10am-11:30am PST
    • Session 7: Nov.20th 10am-11:30am PST
    • Session 8: Nov.22th 10am-11:30am PST

    • 12 hours/ 8 sessions
    • 8 lectures / 8 hands-on projects
    • Live Sessions, Real time interaction
    • Watch sessions replay anywhere any time

    Check the content tab for full course outlines.

    Developers, data scientists, students.

  • Basic familiarity with machine learning
  • AWS account (its free to sign up)
  • No coding prerequisite. We will provide self paced exercises where attendees, if interested, can code in Python, Java or Javascript.
    We believe the course will be helpful for you like majority of other attendees. Even if you can find it not in your expectation level you will get full refund upon request before the first session ends (Oct 30th 12pm PT).

    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 notes

  • Certificate of completing course is available upon request
  • Job referral service is available, contact us for details
  • 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 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 3: 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 4: 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 4: 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 5: 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 5: Attendees will build an AI for Customer Appointment planning and integrate it with an application code module in the language of their choice

    Module 6: 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 6: Attendees will build an AI with an open source dataset and test for Bias.

    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 6: 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
    In this final session, 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, attendees will experiment with multiple iterations of the AI lifecycle in a production context and see some of these advanced concepts in action.
    What attendees will learn:
    • Aspects of production AI that apply to all the use cases covered in this series, and to many other (if not all other) production AI
    • How to think about and execute multiple iterations of the production lifecycle over time
    • How to manage production application changes and production AI upgrades in concert
    • Lab 8: Exercise in multiple iterations of the AI lifecycle using a business use case with publicly available data and multiple data versions
    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:
      $199 $199 USD
    • Students enrolled:48
    • Status: course ended
    • Course Preview:

    • Need help? Send Question