Artificial Intelligence - AI5

AI-5: Productionizing AI (MLOps)

Your journey in Deep Learning has lead you here. You are now an expert at building everything from computer vision to language to generative to reinforcement models. Those awesome models you trained now sit in notebook files right? What if you want to give life 🌱 to these models? Maybe build an AI powered App 😁

This brings us to AI5!

Welcome to AI5.

This course aims to review existing Deep Learning flow while applying it to a real-world problem. Then we will build and deploy an application that uses the deep learning model to understand how to productionize models. This course follows the Univ.AI model of balancing between concept, theory, and implementation.

Split into three parts; the course starts with the review of Deep Learning concepts for data and modeling and how to apply them to different tasks, including vision and language tasks. The next part will be Development, where you use the models you trained in part 1 and incorporate them into real-world applications. Finally, you will Deploy the application in Google Cloud Platform (GCP). The three parts will cover in detail topics such as Transfer learning, Containerization using Docker, and Scaling deployments using Kubernetes.

At the end of this module, you will build efficient deep learning models and design, build and deploy applications that scale.

This page introduces you to the team, the basic instructions, the schedule, and various elements of our class.

Interested in joining?

If you would like to apply to this course, please go here.

We also provide this course as part of our Masters and Accelerated program, check this link out to get more information and apply.

The Team

Dr. Pavlos Protopapas

You can read more about him here.

Shivas Jayaram

You can read more about him here.

The Coursework

We have very carefully designed the coursework to give you, the student, a wholesome learning experience.

Each week shall include:

Session - What to expect

Before the session begins, students are expected to complete a pre-class reading assignment and and attempt a quiz based on the same.

A session will have the following pedagogy layout which will be repeated three times:

After the session, students are expected to complete a short post-class quiz based on the principal concepts covered in class.

Lab - What to expect

A lab is a one hour session that is divided into 3 major parts.


Module Concepts
Project Outline
Introduction to Projects
  • Problem Definition
  • Proposed Solutions
  • Project Scope
Deep Learning
  • Data Pipelines
  • Tensorflow Data
  • Tensorflow Records
  • Dask
  • Cloud Storage Buckets
  • Computer Vision: Classification
  • Computer Vision: Segmentation
  • NLP & Language Models
  • Transfer Learning and SOTA Models
  • Distillation and Compression
  • Virtual Environments, Virtual Boxes, and Containers
  • Containerization & Docker
  • App Design
  • Setup and Code organization
  • APIs and Model serving
  • App frontend
Deployment, Scaling, & Automation
  • Google Cloud Platform (GCP)
  • Kubernetes
  • Ansible


During the entire course you will work in teams and implement a project. The various topics in the class are designed to help you build milestones in an incremental fashion and build towards the end goal. The final outcome with your project will be a fully working AI App.

Here are some of the projects:

Mushroom Identification (In class demo)
  • Pavlos likes to go the forest for mushroom picking
  • Some mushrooms can be poisonous
  • Help build an app to identify mushroom type and if poisonous or not

Austin Pets Alive (APA)
  • APA is an association of pet owners
  • They would like to help future dog owners find a dog who is a perfect fit for them
  • Help build an app that can help owners find the right pet

Visual Question Answering
  • The VQA dataset contains open-ended questions about images

Please find a more detailed summary of all projects here.

The Class

Welcome Session - Preparing for this class

There will be a Welcome Session scheduled on Monday, 9th August 2021 at 7:30 PM IST for all registered students. Please check your mail for more information.

High level course schedule

NOTE: Below timings are in IST

Lecture Sessions:

Lab Sessions:

Office hours:

Course Pre-Requisites

Your are expected to know the following:
* Good working knowledge of python
* Good understanding on the Tensorflow Deep Learning framework
* Basic shell commands

Install Docker

Install Docker Desktop for your operating system.

Install VSCode

Follow the instructions for your operating system.
If you already have a preferred text editor, skip this step.

Diversity & Inclusion

We actively seek and welcome people of diverse identities, from across the spectrum of disciplines and methods since Artificial Intelligence (AI) increasingly mediates our social, cultural, economic, and political interactions [1].

We believe in creating and maintaining an inclusive learning environment where all members feel safe, respected, and capable of producing their best work.

We commit to an experience for all participants that is free from – Harassment, bullying, and discrimination which includes but is not limited to:


[1] K. Stathoulopoulos and J. C. Mateos-Garcia, “Gender Diversity in AI Research,” SSRN Electronic Journal, 2019 [Online]. Available:

Logistics - What you need to begin?

We assume you have a Univ.AI account, created when you signed up at If not, email

Education software we use