Nice paper (ft @daphneipp @florian_tramer @katherine1ee +more) that argues looking at verbatim memorization is inadequate when considering ML privacy risks It also has the most interesting author ordering I've ever seen. So much for alphabetical or random https://
arxiv.org/abs/2210.17546
MACHINE LEARNING
-
ML Privacy Risks Beyond Verbatim Memorization Research
By
–
-
Future perspectives on polynomial models in physics
By
–
Some day humans will find it so quaint that polynomials were our best models of Physics
-
Cohere Python SDK: Add NLP Features to Your App
By
–
Add powerful NLP functionality into your app, like sentiment analysis and text summarization, with Cohere's Python SDK. In this tutorial, we show you how – https://
hubs.li/Q01ryKFW0 -
AI Builders Need Artificial Intelligence Most
By
–
The people building #artificialintelligence are the ones who need AI the most https://
zdnet.com/article/the-pe
ople-building-artificial-intelligence-are-the-ones-who-need-ai-the-most/
… @zdnet #AI #MachineLearning #DataScience #Robots #BigData #Analytics #100DaysofCode #IoT #serverless #womenwhocode #Python #DigitalTransformation #TensorFlow #DeepLearning -
ICLR2023 Paper Reviews Spark Discussion on Research Quality
By
–
#ICLR2023 reviews are out… and seem incredibly brutal for a couple of papers that I really like! (by others, not by me) Good luck and happy weekend to everyone…
-
Improving Fine-Tuning Capabilities for Better AI Customization
By
–
still have a lot to figure out, but we definitely want to let people do more and better fine-tuning
-
Investment and Machine Learning Specific Sessions Overview
By
–
no–this is an investment and some ML-specific sessions, not an accelerator-like thing
-
BTC Cyclic Bottom Prediction Confirmed by AI Analysis
By
–
Bro, we had been screaming $BTC cyclic bottom, even the AI of myself.
-
Research on AI Example Benefits: Output Syntax and Label Space Learning
By
–
I think what Min et al. shows is that much of the benefit of examples is learning the output syntax and label space. Results aren’t as clean as this anecdote suggests by itself, e.g. OOD labels dramatically hurt performance.
-
Few-shot Prompt Setup Notes for Scaling Law Experiments
By
–
Some setup notes (cc @EthanJPerez
) – We used the exact 2-shot prompt for Quote Repetition, which is already U-shaped for Gopher/Chinchilla – We used fewer shots for Hindsight – We did few-shot instead of 0-shot for Negation QA – We also showed inverse scaling up to PaLM 62B