Build AI applications from end to end

Description
Content
Speaker
COURSE OBJECTIVES:
In this course you will learn how to train and deploy ML models in the Amazon Web Services (AWS) Cloud. This includes how to use Amazon S3 to store your data, AWS Sagemaker to train ML models, how to deploy these models as a REST Endpoint, and how to use Amazon Lambda serverless features to connect these models to an external URL to use with your applications. We will also test out the REST endpoint using a Python application.
For this exercise we will use an example of Bank Churn (predicting whether a bank customer is likely to leave the bank). We will provide sample datasets and python programs to run with this use case.
This workshop is fun and exciting and will show you how to use Cloud AI services to not just train your models but also how to deploy them and use them in real life for your smart applications. You can use these techniques to add ML to your development projects, add ML to your applications, or to build new applications.

COURSE SCHEDULE:
  • Session 1: Aug 29th 9am-12pm PT

COURSE INCLUDE:
  • 3 Hours/ 1 Session
  • Lectures / hands-on code labs
  • Live session and real time interaction
  • Watch session replay anywhere any time

COURSE CONTENT:
Check the content tab for full course outlines.

WHO SHOULD LEARN:
Developers, data scientists, students.

PREREQUISITE:
  • Basic familiarity with machine learning
  • AWS account (its free to sign up)
  • SESSION REPLAY
    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

    Module 1: Lectures
  • Lecture: AI Cloud tools we will use and how storage, ML models, and deployments work in AWS
  • Lecture: configure AWS and the settings you will need to use the AI Cloud tools correctly and efficiently
  • Module 2: Code labs
  • Hands on lab 1: Run through the use case yourself. Dataset and sample python programs will be provided.
  • Hands on lab 2: Connect your deployed AI model to a python application and learn how to use and test your modelCode lab
  • Additional tips on other use cases
  • Topics covered:
  • AI Cloud services overview, focusing on using AWS Cloud
  • Full model lifecycle - how to train your model, deploy it, and connect it to an application
  • A business use case - Bank Churn
  • Dataset preparation and feature engineering
  • Model training with several ML techniques for Classification (KNN, Linear Learner, XGBoost and Factorization Machines)
  • Model evaluation metrics (Accuracy)
  • Model deployment as a REST endpoint
  • How to use your model predictions inside a Python application, deploy and test
  • 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: On-demand
    • Venue: Online
    • Fee:
      $39 $19
    • Students enrolled:93
    • Status: learn on-demand
    • Preview this course:
    • Help? Send Question
    Enroll This Course