Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

University of Washington

Machine Teaching for Autonomous AI

University of Washington via Coursera

Overview

Just as teachers help students gain new skills, the same is true of artificial intelligence (AI). Machine learning algorithms can adapt and change, much like the learning process itself. Using the machine teaching paradigm, a subject matter expert (SME) can teach AI to improve and optimize a variety of systems and processes. The result is an autonomous AI system.

In this course, you’ll learn how automated systems make decisions and how to approach building an AI system that will outperform current capabilities. Since 87% of machine learning systems fail in the proof-concept phase, it’s important you understand how to analyze an existing system and determine whether it’d be a good fit for machine teaching approaches. For your course project, you’ll select an appropriate use case, interview a SME about a process, and then flesh out a story for why and how you might go about building an autonomous AI system.

At the end of this course, you’ll be able to:
• Describe the concept of machine teaching
• Explain the role that SMEs play in training advanced AI
• Evaluate the pros and cons of leveraging human expertise in the design of AI systems
• Differentiate between automated and autonomous decision-making systems
• Describe the limitations of automated systems and humans in real-time decision-making
• Select use cases where autonomous AI will outperform both humans and automated systems
• Propose an autonomous AI solution to a real-world problem
• Validate your design against existing expertise and techniques for solving problems

This course is part of a specialization called Autonomous AI for Industry.

Syllabus

  • An Introduction to Autonomous AI & Machine Teaching
    • This module lays the foundation for this course and the entire specialization. You'll learn what makes autonomous AI different from other forms of artificial intelligence. You're invited to take a behind the scenes look at some organizations using autonomous AI and hear from operators and managers about the benefits they're realizing by harnessing autonomous AI. The focus will then transition to you! You'll explore five different mindset profiles that describe different approaches to building AI systems.
  • Analyzing the Problem
    • Not all problems are right for an autonomous AI solution. In this module, we explore types of automated systems and their strengths and limitations for various issues. You'll learn how to determine whether a problem needs a solution that goes beyond automated systems and into useful AI.
  • Learning the Solution
    • In the last module we looked at "automated" systems (math, menus, and manuals); examining situations where they excel and understanding their limitations. In this module we'll focus on "autonomous" systems such as: machine learning (ML), reinforcement learning (RL), neural networks (NN) and deep reinforcement learning (DRL); assessing both the strengths and weaknesses of each autonomous system. Lastly you'll see how "machine teaching" can tap into the strengths of all the automated and autonomous systems.
  • Storytelling
    • Wondering what has storytelling has got to do with AI? Good storytelling is a tool of persuasion. Dry facts and data are not as compelling as persuasion arguments. In the real world someone has to fund the development of your autonomous AI design, and you need to tell that person a persuasive story.

Taught by

Kence Anderson

Reviews

4.8 rating at Coursera based on 17 ratings

Start your review of Machine Teaching for Autonomous AI

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.