https://medium.com/understanding-recommenders/what-does-it-mean-to-give-someone-what-they-want-the-nature-of-preferences-in-recommender-systems-82b5a1559157 What Does it Mean to Give Someone What They Want? The Nature of Preferences in Recommender SystemsLuke Thorburn, Jonathan Stray, Priyanjana BenganiMar 11 “We’ll propose… concrete ways to build
What I Read: Transformers Training
https://www.borealisai.com/research-blogs/tutorial-17-transformers-iii-training/ Tutorial #17: Transformers III Training08/06/2021P. Xu, S. Prince “…we discuss challenges with transformer training dynamics and introduce some of the tricks that practitioners use to get transformers to converge.”
What I Read: Learning to Imitate
https://ai.stanford.edu/blog/learning-to-imitate/ Learning to ImitateDivyansh GargNovember 1, 2022 “A key aspect of human learning is imitation…. How can we enable our artificial agents to similarly acquire such fast learning ability?”
What I Read: Federated, Protects Privacy
https://pair.withgoogle.com/explorables/federated-learning/ How Federated Learning Protects Privacy “With federated learning, it’s possible to collaboratively train a model with data from multiple users without any raw data leaving their devices.”
What I Read: New Chip, AI
https://www.quantamagazine.org/a-brain-inspired-chip-can-run-ai-with-far-less-energy-20221110/ New Chip Expands the Possibilities for AIAllison WhittenContributing WriterNovember 10, 2022 “An energy-efficient chip called NeuRRAM fixes an old design flaw to run large-scale AI algorithms on smaller devices,
What I Read: Data Pipeline Smoke Tests
https://dagster.io/blog/smoke-test-data-pipeline The Unreasonable Effectiveness of Data Pipeline Smoke TestsSandy RyzaOctober 19, 2022 “Data practitioners waste time writing unit tests to catch bugs they could have caught with smoke tests.”