Expand the section navigation mobile menu
Machine Learning Banner

Data Analytics and Machine Learning (ML Ops) on the Cloud

Sign up to receive emails about OU's Machine Learning Program. 


Course Description:
Machine Learning as a field is now incredibly pervasive, with applications in areas including business intelligence, homeland security, biochemical interaction analysis, infrastructure monitoring, and astrophysics. Deep learning is a branch of machine learning concerned with the development and application of modern neural networks. Deep learning algorithms extract layered high-level representations of data in a way that maximizes performance of a give task. Deep learning is behind many recent advances in AI, including Siri’s speech recognition, Facebook’s tag suggestions, machine language translation and self-driving cars. This course is an introduction to Machine Learning using TensorFlow 2.0, which is a very popular framework for building predictive models. The course will provide a step by step approach to building complex machine learning models starting from the very basics concepts of machine learning and the TensorFlow 2.0 framework from Google. We will be using a variety of tools and platforms such as Python, TensorFlow/Keras, and Google Collaboratory Notebooks for building, testing, and deploying machine learning models.

This 7-week program contains 42 contact hours of online, synchronous instruction and is broken into 3 modules and covers fundamental topics exposing students to Artificial Intelligence and Machine Learning. The program is ideal for graduating and working engineers new to the Artificial Intelligence and Machine Learning world.

This program contains specializations for Retail, Healthcare, Financial Services and Industrial / Manufacturing. You can select one or more specializations as part of the course (each specialization is 3-5 weeks long). You will understand the use cases defined below and implement one use case end-to-end as a part of your project.

A PACE Certificate of Achievement will be awarded upon successful completion of the program.

REGISTER

Learning Outcomes
By the end of the course, students will be able to: 

  • Explain how machine learning models work
  • Frame tasks into machine learning problems
  • Use machine learning toolkits to implement the designed models
  • Justify when and why specific machine learning techniques work for specific problems
  • Build, test, and deploy complex machine learning models to solve specific problems

Tentative Course Outline

Each module contains corresponding hands-on labs covering module topics.

Module 1: Python Basics - 1 week
  • Python Tutorial, including:
    • Data Types & Strings
    • User Defined Functions
    • Pandas Series
    • Lambda & Map
    • Introduction to Classes and Objects

This module covers the fundamentals of Python programming. After completing this module, students will be able to write reasonably complex Python code for working with data. The following table shows the topics covered in this module.

Python Basics

Topics Details

Python Basics

  • Getting Started, Data Types & Strings, List & Tuples, Sets & Dictionary, If Else Statement, For & While Loop, User Defined Functions, Read & Write a File, Pandas Series, Data Frames, Lambda & Map

Data structures

  • Lists, Tuples, Dictionary.
  • Using Built-in modules and functions for strings, computations and dates.
  • Object-Oriented Programming (OOP) principles.

Using Modules

  • Creating and using Functions.
  • Creating a Module in class; Calling a Module; Returning value from a Module; Adding a Method that takes parameters;

Introduction to Classes and Objects

  • Creating a Class; Creating an Object; Using an Object; Adding Instance variables; Controlling accessibility; Naming conventions for class members. Inner Classes.
  • Class Constructors; Parameterized Constructors.
  • Inheritance. Overload.

Files, streams, database connectivity and API

  • Open, Traverse, Read and Create Files: databases, csv, txt and Json Files.
  • Connect to a database, create Database, drop a database, create a table, alter tables, drop a table, insert, delete, update records, query a database and display results.
  • Connecting to different APIs
Module 2: Machine Learning using TensorFlow - 4 weeks
  • Introduction to Machine Learning
  • What is Machine Learning?
  • Introduction to TensorFlow
  • Building TensorFlow Models
  • Scaling-up and Model Deployment

This module focuses on the fundamentals of machine learning and the commonly used ML and Deep Learning models on the Google Cloud platform. Building models using TensorFlow, training and assessing their performance using TensorBoard, and deploying the models will be discussed.

Machine Learning using TensorFlow 2.0

Topics Details

Introduction to Machine Learning

  • What is Machine Learning?
  • Machine Learning vs. Data Science
  • How does everything fit in the AI & ML world?

What is Machine Learning?

  • Getting started with Machine Learning
  • Setting up your Cloud environment (GCP)
  • Understanding the basics of Google Cloud
  • Developing first Machine Learning model - Regression
  • Developing Machine Learning model - Classification  

Introduction to TensorFlow

  • How does TensorFlow Work?
  • Introduction to Neural Nets
  • Getting Started with TensorFlow
  • Differences between TensorFlow 1.x and TensorFlow 2.x

Building TensorFlow Models

  • Getting started with TensorFlow ML Models
  • Understanding the dataset
  • Preparing to train the model
  • Training a Deep Neural Network Model
  • Understanding TensorBoard
  • What is Feature Engineering?
  • Improving Model Performance - Feature Engineering

Scaling-up and Model Deployment

  • Planning the Cloud Deployment
  • Setup the storage buckets
  • Enable API & Services
  • Create Service Account Key
  • Packaging up the code
  • Running the ML Job on the Google Cloud
  • Deploying a ML Model

Labs for Module-2
Lab1: Implement a Linear Regression and KNN Model.
Lab2: Create a model using TensorFlow - Feature Engineering for a DNN Model 
Lab3: Improve the model performance using Feature Engineering.
Lab4: Deploy the TensorFlow model using Flask API.

Module 3: Industry Focus - 3 weeks

This module is industry specialization for Retail, Healthcare, Financial Services and Industrial / Manufacturing. Students can select one or more specializations as part of the course. This module will focus on the use cases defined below, and students will implement one use case end-to-end as part of the capstone project.


Industry Focus Use Cases

Retail

  • Demand Forecasting
  • Retail Search
  • Product Recommendations
  • Inventory Optimization

Healthcare

  • Telehealth / Virtual Care
  • Interoperability Accelerator
  • Hospital Impact Forecasting
  • Biomedical Data Analytics

Financial Services

  • Anti-Money Laundering (AML)
  • Know Your Customer (KYC)
  • Digital Social Safety Nets
  • Lending Doc Processing

Industrial / Manufacturing

  • Industrial Adaptive Controls
  • Manufacturing Visual Inspection
  • Logistics Optimization
  • Connected Operations

Labs for Module-3
Lab1: Understand a business problem and implement an exploratory data analysis using Python. 
Lab2: Create a machine learning model using TensorFlow 
Lab3: Improve the model performance using Feature Engineering
Lab4: Deploy the TensorFlow model using Flask API

Instructor Information
Name: Vijayan Sugumaran
Title: Distinguished Professor of Management Information Systems
Contact Information: [email protected]

Name: Naresh Jasotani
Title: Specialist Customer Engg. (AI / ML, Data & Analytics)

Google Detroit Office
Contact Information: [email protected]

Professional and Continuing Education

Pawley Hall, Room 440G
456 Pioneer Drive
Rochester, MI 48309-4482
(location map)
(248) 370-3177