PyData Global talk covering tools from geometry/topology and their uses in public health, public policy, and social good initiatives. Examples include food price prediction, COVID policies, public health interventions, and fair AI.
2. Who am I?
◦ Author of forthcoming book, The
Shape of Data
◦ Former public health practitioner
◦ Researcher on spatial and temporal
analytics
◦ Miami sociologist and advocate
4. Persistent Homology
◦ From a branch of math called topology that
deals with global properties of an object
◦ Creates series of distance-based objects
(simplicial complexes)
◦ Tracks features across series
◦ Can be used to compare data over time,
geography, or samples
◦ Easy-to-visualize plots for each feature-tracking
dataset
◦ Connection to Euler Characteristic
6. Generative AI and
Diffusion Methods
◦ Deep learning algorithm that can couple
with diffusion to evolve a picture or
image
◦ Deep neural network architecture to create
an image from text
◦ Differential equation/geometry algorithms
to evolve the image to the artist’s liking
◦ Finding popularity in art and generation of
educational material
12. Good Resources
◦ Persistent Homology
◦ TDAstats or TDApplied in R
◦ Persim or Giotto in Python
◦ Forman-Ricci curvature
◦ Contact me on LinkedIn for code: https://www.linkedin.com/in/colleenmfarrelly/
◦ Text-to-Image
◦ NightCafe
◦ OpenAI’s DALL-E