machine learning 相关 AI 资讯 · AITOP

8月25日

03:03

官方账号LangChain@LangChainAI

精选

Join the LangChain event on August 27th in Sunnyvale. Keynote by @hwchase17, insights from Expedia's Director of Machine Learning, deep dives on agent harnesses and LangSmith Engine, hands-on workshop, and networking with fellow agent builders. RSVP required.

推荐理由：Join the LangChain event for insights on agent development, learn from Expedia's ML Director, and network with other builders. Don't miss the hands-on workshop!

原文

8月24日

10:02

官方账号arXiv cs.LG@Adam Noonan

This paper discusses the challenges in setting thresholds in machine-learning systems, particularly when calibration examples are not independent. It introduces a new approach to calculate the effective sample size for thresholds under clustering, showing that the current correction in the conformal literature is incorrect. The study also highlights the importance of considering the threshold level for each dataset, as the effective sample size varies with the threshold setting. The research is based on a calibration set of 25,028 examples and measures the reliability of about 1,300 thresholds.

论文 thresholds machine learning calibration sets

推荐理由：This paper offers a fresh perspective on threshold setting in machine learning, providing a new method to calculate effective sample sizes under clustering. It's a must-read for those interested in improving the reliability of machine learning systems.

原文

8月21日

10:40

官方账号arXiv cs.AI@Jianghai Li, Pavel Kuznetsov, Yury Yanovich, Konstantin Nott-Whaley, Igor Vodolazov

This paper focuses on Solana memecoins, detecting rug pulls using machine learning models like XGBoost. It reveals most memecoins show rug pull characteristics within an hour of launch, emphasizing the need for short-horizon prediction. The study also finds multi-source data fusion improves detection reliability across platforms like PumpFun and Raydium.

论文 Solana memecoins rug pull detection

推荐理由：This study offers a practical framework for detecting Solana memecoin rug pulls, using XGBoost and multi-source data fusion, providing valuable insights for investors in the DeFi space.

原文