Intro Data Science: Algorithmic Bias

Lecture

Slides: .pptx .pdf

Bias in Word Embeddings

Bias in Word Embeddings notebook: .html .pdf.

The notebook is hosted on github.

Background information

• Principal Component Analysis: PCA
• WEVI: word embedding visual inspector

See also

Great starting points to dive deeper into the research into how to assess bias:

• Tutorial auditing Black Box models from FAT* 2018
• Google’s What-if Tool
• “Why Should I Trust You?”: Explaining the Predictions of Any Classifier: Lime

You might also be interested in MLJAR: Machine Learning for Humans.