NodeJS, ML, K8s and Unethical Face Recognition
summary
Prototype combines Node.js, Twitter API, face-api.js and a sentiment library to pull follower profile pictures, run single-image recognition (often correct from one reference photo), score tweet sentiment, and store results via Mongo-like DB. Processing is queued with RabbitMQ + Kubernetes so CPU-heavy face descriptors scale by adding consumers; deployment uses containers on OpenShift. Demo shows some false positives (several mismatches, one person scored zero) and the system mostly works but exposes clear ethical and accuracy limits.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 2:08What I wanted to build
- 9:20What is ML
- 15:35Face Recognition
- 19:34Sentiment Analysis
- 27:10Messaging queues
- 30:14Kubernetes
- 31:58Openshift
- 33:14Demo
- 35:07Outro
related talks
39mNodeJS, ML, K8s and Unethical Face Recognition
53mNodeJS, ML, K8s and Unethical Face Recognition
01h 05mIntro to machine learning in Node
54mIntroduction to machine learning in Node.js
59mMachine Learning and Big Data Magic with Node.js and Google Cloud
23mReal Time Machine Learning With Node js
26mNew Face, Who Dis? Recent Adversarial Approaches to Facial Recognition
40mNew Face, Who Dis? Protecting Privacy in a World of Surveillance