A Tester's Guide to Testing AI Applications thumbnail

A Tester's Guide to Testing AI Applications

23 Jan 2018
  • Locked
Self-driving cars, intelligent digital assistants, making parole decisions, detecting, developing new treatments and drugs, and reviewing legal contracts and documents – the use of Artificial Intelligence (AI) technology is increasingly finding its way into mainstream software development. If you are not currently working on a product or project that includes AI technology, you will likely be within the next five years.

While there are a great many resources covering AI from a development perspective, there are few that deal with testing AI-based software despite the challenges and risks this poses. For example:

 How do we test software… 
  • When the decision logic is not clearly defined?
  • When the results may be wrong, and that’s OK sometimes
  • That learns and adapts based on interactions
  • To find the problems that will matter when the input domain is complex and massive
  • That may need to collaborate or compete with other AI software.

These are just some of the challenges of testing AI-based software and while traditional software test design ideas can help but are generally not enough to explore the capabilities of AI-Based software.

In this Masterclass, Bill will take you beyond the AI hype and give you a pragmatic and useful perspective of what AI is. You'll then be shown how testing an AI-based application differs from more traditional applications and explore some strategies to help you tackle testing of AI-based applications.

Comments

Sign in to comment
Explore MoT
Leading with AI - The London Edition image
Fri, 19 Jun
A half-day educational experience to navigate the world of AI
A Software Tester’s Guide To Chrome Devtools image
Learn how to dig deeper into the Web with the use of Devtools
This Week in Quality image
Debrief the week in Quality via a community radio show hosted by Simon Tomes and members of the community
Subscribe to our newsletter