#Python #FeatureEngineering Cookbook with 70+ recipes for creating, engineering, & transforming features for #MachineLearning models (2nd Edition): http://
amzn.to/3Ssdh5X via @PacktPublishing ————
#AI #BigData #DataStrategy #DataLiteracy #DataScience #DataScientists #Coding #ML
RESEARCH
-
Python Feature Engineering Cookbook: 70+ Recipes for Machine Learning
By
–
-
Excellent Data Science For Dummies 3rd Edition Book Recommendation
By
–
Excellent book: “#DataScience For Dummies” 3rd edition, by @Strategy_Gal Get it here: http://
amzn.to/3AJ22ec
————
#BigData #DataScientists #AI #MachineLearning #DataStrategy #Analytics #AnalyticsStrategy -
Understanding Randomness in Life and Decision Making
By
–
“How Randomness Rules Our Lives” — You know it to be true! “Fooled by Randomness” — Don’t be! See the books: https://
amzn.to/2WO1Wka https://
amzn.to/3dwTnjA
———————
#BigData #DataScience #AI #MachineLearning #DataLiteracy #Statistics #StatisticalLiteracy #Probability -
The Danger of Decision Making Based on Averages
By
–
The Danger of Making Decisions based upon Averages: http://
bit.ly/2S3eK5O by @schmarzo See the book "The Flaw of Averages” http://
amzn.to/3C2CCtY
———
#StatisticalLiteracy #MachineLearning #AI #BigData #Analytics #DataScience #Statistics #DecisionScience #DataLiteracy -
Europa Clipper: Life Detection More Likely Than AGI
By
–
Europa Clipper, launching Oct 2024, reaches Europa (Jupiter) in 2030, *may* be able to detect life if life is there. Should it do so I will find it much less surprising than if we have AGI by then despite what NVIDIA CEO might predict. Same for 2040, 2050, or any 20xx.
-
Retrieval-Augmented Fine-Tuning: Combining RAG and Fine-tuning
By
–
10/ Retrieval-Augmented Fine-Tuning Combines the benefits of RAG and fine-tuning to improve a model's ability to answer questions in "open-book" in-domain settings; combining it with RAFT's CoT-style response helps to improve reasoning.
-
LLMs Leak Proprietary Information Through API Logits
By
–
8/ LLMs Leak Proprietary Information Shows that it’s possible to learn a large amount of non-public information about an API-protected LLM using the logits; with a relatively small number of API queries, the approach estimates that the embedding size of gpt-3.5-turbo to be
-
DROID: Large-Scale Open-Source Robot Manipulation Dataset
By
–
9/ DROID
— DAIR.AI (@dair_ai) 24 mars 2024
An open-source, large-scale robot manipulation dataset to train and build more capable and robust robotic manipulation policies; it contains 76K demonstration trajectories, collected across 564 scenes and 86 tasks.https://t.co/8xAIyepZ0u9/ DROID An open-source, large-scale robot manipulation dataset to train and build more capable and robust robotic manipulation policies; it contains 76K demonstration trajectories, collected across 564 scenes and 86 tasks.
-
Agent-FLAN: Fine-tuning Language Models for Enhanced Agent Performance
By
–
7/ Agent-FLAN Designs data and methods to effectively fine-tune language models for agents, referred to as Agent-FLAN; this enables Llama2-7B to outperform prior best works by 3.5% across various agent evaluation datasets.
-
RankPrompt: Self-Ranking Method for Better LLM Reasoning
By
–
5/ Step-by-Step Comparisons Make LLMs Better Reasoners Proposes RankPrompt, a prompting method to enable LLMs to self-rank their responses without additional resources.