From the course: Applied AI Auditing in Python
Join today to access over 24,800 courses taught by industry experts.
Explore a dataset for representation - Python Tutorial
From the course: Applied AI Auditing in Python
Explore a dataset for representation
- [Instructor] When inspecting training data for representation, there are several key steps we can take to ensure a thorough and inclusive analysis. First, we should conduct a high-level inspection to identify groups that may be underrepresented or excluded from a dataset. It's crucial to recognize that many public datasets, such as the census, often fail to capture the full spectrum of identities. For example, they may only gather information based on the gender assigned at birth, thereby excluding transgender and non-binary individuals. Certain populations are systemically overlooked in many data sets, including undocumented individuals, people with invisible disabilities, and those who identify as mixed race or biracial. It's essential to acknowledge that bias also exists at the intersection of these identities, leading to unique and compounded experiences of discrimination. To uncover these intersectional biases, we can manually explore the data, find guidance from prior…
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.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.