Context

...

Background material

Articles & explainers

• https://ig.ft.com/generative-ai/

• https://towardsdatascience.com/transformers-in-depth-part-1-introduction-to-transformer-models-in-5-minutes-ad25da6d3cca

Videos

• https://www.youtube.com/watch?v=zjkBMFhNj_g

  • Very thorough and clear explainer of how LLMs work

• https://www.youtube.com/watch?v=2eWuYf-aZE4

  • Goes through now neural networks work, and how they’re used in LLMs, image generators, etc

• https://www.youtube.com/watch?v=4RixMPF4xis

Courses & tutorials

• https://developers.google.com/machine-learning

• https://www.cloudskillsboost.google/course_templates/536

• https://www.cloudskillsboost.google/course_templates/539

• https://www.cloudskillsboost.google/course_templates/556

• https://huggingface.co/learn/nlp-course/chapter1/1

What should we talk about

...

• A leaderboard of face verification models

  • Just shows accuracy - would be great to augment with robustness

• Models available via the DeepFace (PyPi | GitHub) library (with % score against Labeled Faces in the Wild dataset):

  • VGG-Face (97.78%)

  • Google FaceNet (99.63%)

  • OpenFace (93.8%)

  • Facebook DeepFace (97.35%)

  • DeepID (99.15%)

  • Dlib (99.38%)

  • ArcFace (99.40%)

• OpenCV Face Recognition

• face.evoLVE

• Models available via FaceTorch:

  • MagFace+UNPG

  • AdaFace

  • Also includes a deepfake detector that might be worth looking into?

Liveness detection

Some background information from FaceTec

Pattern / anomaly detection

...