From the course: AI Accountability: Build Responsible and Transparent Systems (2022)
Unlock the full course today
Join today to access over 24,800 courses taught by industry experts.
Supervised and unsupervised learning
From the course: AI Accountability: Build Responsible and Transparent Systems (2022)
Supervised and unsupervised learning
- [Instructor] Before we go much further in our discussion of AI and the challenges that can come up, I should make it clear that just like there are many different jobs in an office, each of which has its own responsibilities and challenges, there are many variations of AI. So we're not talking about the same thing all the way through. More accurately, there are many kinds of machine learning tasks and like jobs in an office, they have their own responsibilities as well as their own requirements and challenges. For example, here are the three of the most common learning tasks. They include unsupervised learning, which is clustering similar cases, putting like with like, like sorting vegetables. Supervised learning which is classifying or categorizing new cases into existing categories. Which bag does this bean go into? Or reinforcement learning, which is training an algorithm to maximize performance on a task, often used in teaching algorithms, complex skills like playing a video…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Contents
-
-
-
-
The challenge of classification errors3m 39s
-
(Locked)
The causes of classification errors6m 18s
-
(Locked)
Bias in AI3m 50s
-
(Locked)
Supervised and unsupervised learning8m 16s
-
(Locked)
Biased labeling of data7m 15s
-
(Locked)
Construct validity6m 14s
-
(Locked)
The absence of meaning4m 54s
-
(Locked)
Vulnerability to attacks4m 45s
-
-
-
-
-
-