Scale By the Bay 2021 intro video by Adarsa Sivaprasad
summary
Concrete notes on turning ML prototypes into production: embedding recommendation engines and knowledge graphs into products, building continuous deployment pipelines for deep models, and automating A/B testing and data quality checks. Explains UI choices that surface model explainability, privacy and bias visibility, and UI feedback loops for correct labeling and reinforcement scenarios. Mentions work on Sunbird, Content Auto Tagging for adaptive recommendation and NLP for Indian languages, with practical examples of what was built and how it performs.
AI-written summary · about
related talks
50mAnalytics – Balancing ‘Advanced’ and ‘Actionable’
22mReal-world applications of machine learning: Beyond the hype
48mThe Missing Step in Moving from Data to Models
45mContent recommendation at iFood scale
31mBeyond the Black Box: Interpreting ML Models with SHAP
01h 26mSaturday Keynotes
31mWhy data science and UX research should be best friends
11mData-centric AI: A new paradigm