AI Workflow: AI in Production from Coursera

This is the sixth course in the IBM AI Enterprise Workflow Certification specialization. You are STRONGLY encouraged to complete these courses in order as they are not individual independent courses, but part of a workflow where each course builds on the previous ones.

This course focuses on models in production at a hypothetical streaming media company. There is an introduction to IBM Watson Machine Learning. You will build your own API in a Docker container and learn how to manage containers with Kubernetes. The course also introduces several other tools in the IBM ecosystem designed to help deploy or maintain models in production. The AI workflow is not a linear process so there is some time dedicated to the most important feedback loops in order to promote efficient iteration on the overall workflow.

By the end of this course you will be able to:

1. Use Docker to deploy a flask application

2. Deploy a simple UI to integrate the ML model, Watson NLU, and Watson Visual Recognition

3. Discuss basic Kubernetes terminology

4. Deploy a scalable web application on Kubernetes

5. Discuss the different feedback loops in AI workflow

6. Discuss the use of unit testing in the context of model production

7. Use IBM Watson OpenScale to assess bias and performance of production machine learning models.

Who should take this course?

This course targets existing data science practitioners that have expertise building machine learning models, who want to deepen their skills on building and deploying AI in large enterprises. If you are an aspiring Data Scientist, this course is NOT for you as you need real world expertise to benefit from the content of these courses.

What skills should you have?

It is assumed that you have completed Courses 1 through 5 of the IBM AI Enterprise Workflow specialization and you have a solid understanding of the following topics prior to starting this course: Fundamental understanding of Linear Algebra; Understand sampling, probability theory, and probability distributions; Knowledge of descriptive and inferential statistical concepts; General understanding of machine learning techniques and best practices; Practiced understanding of Python and the packages commonly used in data science: NumPy, Pandas, matplotlib, scikit-learn; Familiarity with IBM Watson Studio; Familiarity with the design thinking process.

What's inside

Syllabus

Feedback loops and Monitoring

This module focuses on feedback loops and monitoring. Feedback loops represent all the possible ways you can return to an earlier stage in the AI enterprise workflow. We initially discussed feedback loops in the first course of this specialization; however, here our focus is on unit testing. We are also looking at business value, a very important consideration that often gets overlooked; is the model having as significant effect on business metrics as intended? It is important to be able to use log files that have been standardized across the team to answer questions about business value as well as performance monitoring. You will have an opportunity to complete a case study on performance monitoring, where you will write unit tests for a logger and a logging API endpoint, test them, and write a suite of unit tests to validate if the logging is working correctly.

Hands on with Openscale and Kubernetes

This module will wrap up the formal learning in this course by completing hands on tutorials of Watson Openscale and Kubernetes. IBM Watson OpensScale is a suite of services that allows you to track the performance of production AI and its impact on business goals, with actionable metrics, in a single console. Kubernetes is a container orchestration platform for managing, scheduling and automating the deployment of Docker containers. The containers we have developed as part of this course are essentially microservices meant to be deployed as cloud native applications.

Capstone: Pulling it all together (Part 1)

In this module you start part one (Data Investigation) of a three-part capstone project designed to pull everything you have learned together. We have provided a brief review of what you should have learned thus far; however, you may want to review the first five courses prior to starting the project. A major goal of this capstone is to emulate a real-world scenario, so we won’t be providing notebooks to guide you as we have done with the previous case studies.

Capstone: Pulling it all together (Part 2)

In this module you will complete your capstone project and submit it for peer review. Part 2 of the Capstone project involves building models and selecting the best model to deploy. You will use time-series algorithms to predict future values based on previously observed values over time. In part 3 of the Capstone project, your focus will be creating a post-production analysis script that investigates the relationship between model performance and the business metrics aligned with the deployed model. After completing and submitting your capstone project, you will have access to the solution files for further review.

Good to know

Know what's good

, what to watch for

, and possible dealbreakers

Establishes a learning path for those new to the field by encouraging them to take previous courses in the specialization

Provides hands-on practice with open-source tools and technologies that are industry-standard for deploying AI models in production

Focuses on real-world applications of AI in the context of a hypothetical streaming media company, making the learning experience more relatable and engaging

Requires a solid foundation in data science concepts and machine learning techniques, including knowledge of Python and related libraries

Assumes familiarity with IBM Watson Studio, which may limit accessibility for learners who are not familiar with this platform

Emphasizes feedback loops and monitoring, which are crucial aspects of maintaining and improving AI models in production

Reviews summary

Practical introduction to ai workflow

Learners say that this is a well-designed course with practical elements such as hands-on activities and links to examples. Most students found the course helpful and learned new concepts

Well-structured with clear progression.

"Well Course is well design ....The revision of all Inclusive Course has been summarise ...step by step it reach to level where you can actually start taking Business Decesion in terms of Cost , Profit."

Covers a range of topics in AI workflow.

"Good Valuable Course to know the end to end flow of a problem with solution and the how to part "

Provides helpful code examples to work with.

"great examples"

"Overall the material is good, and I plan to use much of the code I created as well as the solutions as samples."

Offers practical exercises.

"Excellent course.. Provides lots of hands-on activities"

"very helpful to understand and process whole AI workflow"

"Overall the material is good, and I plan to use much of the code I created as well as the solutions as samples."

Could provide more in-depth explanations.

"often it seemed like a topic would be introduced and then a link shared rather than the topic being explained well in this course material."

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in AI Workflow: AI in Production with these activities:

Explore IBM Watson Studio and its capabilities

Show steps

Become familiar with IBM Watson Studio, a platform for developing and deploying AI models.

Browse courses on IBM Watson Studio

Show steps

Sign up for a free IBM Watson Studio account.
Explore the different services and tools available.
Create a project and start building a simple machine learning model.

Create a Glossary of Technical Terminology

Show steps

Develop a comprehensive understanding of key terminologies and concepts used in AI and ML by creating your own glossary.

Show steps

Identify and gather technical terms from the course materials.
Research and define each term accurately.
Organize the terms alphabetically or by category.
Review and refine the glossary regularly.

Attend an online workshop on Kubernetes for AI/ML

Show steps

Expand your knowledge by attending an online workshop focusing on Kubernetes for AI/ML.

Browse courses on Kubernetes

Show steps

Research and identify relevant workshops.
Register and attend the workshop.
Actively participate in discussions and hands-on exercises.

Five other activities

Expand to see all activities and additional details

Show all eight activities

Practice deploying models with Docker and Kubernetes

Show steps

Gain hands-on experience in deploying AI models by practicing with Docker and Kubernetes.

Browse courses on Docker

Show steps

Set up a Docker environment on your local machine.
Create a simple Flask application.
Deploy the application in a Docker container.
Set up a Kubernetes cluster.
Deploy the containerized application on Kubernetes.

Build a simple AI-powered chatbot

Show steps

Apply what you've learned by creating a basic chatbot that interacts with users using natural language.

Browse courses on Chatbot

Show steps

Choose a chatbot platform and framework.
Design the chatbot's conversation flow and intents.
Train the chatbot on a dataset of conversations.
Deploy the chatbot and test its performance.

Compile study materials

Show steps

Review important concepts and coursework by compiling your materials and notes you've gathered throughout the course.

Show steps

Gather and organize notes, assignments, and coursework materials.
Review the compiled materials for key concepts and points.
Highlight and summarize important sections for future reference.

Review 'Machine Learning Engineering' by Andriy Burkov

Show steps

Gain insights into best practices and methodologies for building and deploying production-ready AI systems.

View Machine Learning Engineering on Amazon

Show steps

Read the book and take notes on key concepts.
Summarize the main takeaways and how they relate to the course content.

Develop a performance monitoring dashboard for a deployed model

Show steps

Enhance your understanding by creating a dashboard to monitor the performance of a deployed AI model with IBM Watson Openscale.

Browse courses on Performance Monitoring

Show steps

Choose a deployed model and identify relevant metrics.
Set up IBM Watson Openscale and connect it to the model.
Create visualizations to display key metrics.
Establish alerts and notifications for performance issues.

Career center

Learners who complete AI Workflow: AI in Production will develop knowledge and skills that may be useful to these careers:

Data Scientist

A Data Scientist uses data to solve business problems. They work on all aspects of the data science lifecycle, from data collection and preparation to data analysis and modeling. This course can help you develop the skills you need to become a Data Scientist by providing you with a foundation in the key concepts of data science, as well as hands-on experience with using data to solve real-world problems.

See salaries and explore the career path for Data Scientist

Machine Learning Engineer

A Machine Learning Engineer designs and develops machine learning models to solve real-world problems. They work on all aspects of the machine learning lifecycle, from data collection and preparation to model training and deployment. This course can help you develop the skills you need to become a Machine Learning Engineer by providing you with a foundation in the key concepts of machine learning, as well as hands-on experience with building and deploying machine learning models on IBM Cloud.

See salaries and explore the career path for Machine Learning Engineer

Software Engineer

A Software Engineer designs, develops, and maintains software applications. They work on all aspects of the software development lifecycle, from requirements gathering and analysis to design, development, and testing. This course can help you develop the skills you need to become a Software Engineer by providing you with a foundation in the key concepts of software engineering, as well as hands-on experience with building and deploying software applications.

See salaries and explore the career path for Software Engineer

Data Analyst

A Data Analyst collects, analyzes, and interprets data to help businesses make better decisions. They work on all aspects of the data analysis lifecycle, from data collection and preparation to data analysis and reporting. This course can help you develop the skills you need to become a Data Analyst by providing you with a foundation in the key concepts of data analysis, as well as hands-on experience with using data to solve real-world problems.

See salaries and explore the career path for Data Analyst

Business Analyst

A Business Analyst works with businesses to identify and solve business problems. They work on all aspects of the business analysis lifecycle, from requirements gathering and analysis to solution design and implementation. This course can help you develop the skills you need to become a Business Analyst by providing you with a foundation in the key concepts of business analysis, as well as hands-on experience with using data to solve real-world problems.

See salaries and explore the career path for Business Analyst

Product Manager

A Product Manager leads the development and launch of new products. They work on all aspects of the product lifecycle, from concept development and market research to launch and support. This course can help you develop the skills you need to become a Product Manager by providing you with a foundation in the key concepts of product management, as well as hands-on experience with building and launching new products.

See salaries and explore the career path for Product Manager

Project Manager

A Project Manager plans and executes projects. They work on all aspects of the project management lifecycle, from project initiation and planning to project execution and closure. This course can help you develop the skills you need to become a Project Manager by providing you with a foundation in the key concepts of project management, as well as hands-on experience with planning and executing projects.

See salaries and explore the career path for Project Manager

Technical Writer

A Technical Writer creates documentation for software and other technical products. They work on all aspects of the technical writing lifecycle, from planning and writing to editing and publishing. This course can help you develop the skills you need to become a Technical Writer by providing you with a foundation in the key concepts of technical writing, as well as hands-on experience with writing and editing technical documentation.

See salaries and explore the career path for Technical Writer

Sales Engineer

A Sales Engineer works with customers to identify and solve their business problems. They work on all aspects of the sales process, from lead generation and qualification to closing and follow-up. This course can help you develop the skills you need to become a Sales Engineer by providing you with a foundation in the key concepts of sales engineering, as well as hands-on experience with working with customers to solve their business problems.

See salaries and explore the career path for Sales Engineer

Consultant

A Consultant provides advice and guidance to businesses on a variety of topics. They work on all aspects of the consulting process, from project initiation and planning to project execution and closure. This course can help you develop the skills you need to become a Consultant by providing you with a foundation in the key concepts of consulting, as well as hands-on experience with working with clients to solve their business problems.

See salaries and explore the career path for Consultant

Teacher

A Teacher teaches students at all levels, from elementary school to college. They work on all aspects of the teaching process, from lesson planning and development to instruction and assessment. This course can help you develop the skills you need to become a Teacher by providing you with a foundation in the key concepts of teaching, as well as hands-on experience with teaching students.

See salaries and explore the career path for Teacher

Librarian

A Librarian helps people find and use information. They work in all types of libraries, from public libraries to school libraries to corporate libraries. This course can help you develop the skills you need to become a Librarian by providing you with a foundation in the key concepts of librarianship, as well as hands-on experience with helping people find and use information.

See salaries and explore the career path for Librarian

Archivist

An Archivist preserves and manages historical documents and artifacts. They work in all types of archives, from government archives to corporate archives to university archives. This course can help you develop the skills you need to become an Archivist by providing you with a foundation in the key concepts of archival science, as well as hands-on experience with preserving and managing historical documents and artifacts.

See salaries and explore the career path for Archivist

Museum curator

A Museum Curator manages and cares for a museum's collection of objects. They work on all aspects of museum curation, from collection management and preservation to exhibition design and development. This course can help you develop the skills you need to become a Museum Curator by providing you with a foundation in the key concepts of museum curation, as well as hands-on experience with managing and caring for a museum's collection of objects.

See salaries and explore the career path for Museum curator

Historian

A Historian studies the past and writes about it. They work on all aspects of history, from research and writing to teaching and public speaking. This course can help you develop the skills you need to become a Historian by providing you with a foundation in the key concepts of history, as well as hands-on experience with research and writing.

See salaries and explore the career path for Historian