خدا خیرش بده. اکثر معادلات متداول یادگیری ماشین رو به فرمت لاتک نوشته:

https://blmoistawinde.github.io/ml_equations_latex

این هم یه حجم خوبی از یادداشت‌های با کیفیت در همه حوزه‌های هوش مصنوعی داره. خیلی خوب بود:

https://notesonai.com/

شعر و آهنگ قشنگ:

This is a collection of (mostly) pen-and-paper exercises in machine learning. The exercises are on the following topics: linear algebra, optimisation, directed graphical models, undirected graphical models, expressive power of graphical models, factor graphs and message passing, inference for hidden Markov models, model-based learning (including ICA and unnormalised models), sampling and Monte-Carlo integration, and variational inference.

https://arxiv.org/abs/2206.13446#

‏دکترای ادبیات فارسی دانشگاه آزاد اسلامی رودهن. اسم آقای اخوان ثالت رو هم به انگلیسی ترجمه کرده. قول میدم این مقاله رو نه خودش خونده نه اساتید نه داور مقاله


مسافر
NiNa @Kafiha

The Third Brotherhood 🤌🤌😎😎
حس اسسینز کرید میده 😂

Sir champion, The lord of the paradise هستم 😄😜😌

مدل زبانی Minerva که سه روز پیش توسط گوگل ارائه شد قابلیت حل مسائل ریاضی و جواب سوالات علمی رو طی استدلال به صورت قدم به قدم داره!

لینک بلاگ پست:
https://ai.googleblog.com/2022/06/minerva-solving-quantitative-reasoning.html?m=1

لینک مقاله:
https://arxiv.org/abs/2206.14858

We describe lessons learned from developing and deploying machine learning models at scale across the enterprise in a range of financial analytics applications. These lessons are presented in the form of antipatterns. Just as design patterns codify best software engineering practices, antipatterns provide a vocabulary to describe defective practices and methodologies. Here we catalog and document numerous antipatterns in financial ML operations (MLOps). Some antipatterns are due to technical errors, while others are due to not having sufficient knowledge of the surrounding context in which ML results are used. By providing a common vocabulary to discuss these situations, our intent is that antipatterns will support better documentation of issues, rapid communication between stakeholders, and faster resolution of problems. In addition to cataloging antipatterns, we describe solutions, best practices, and future directions toward MLOps maturity.

https://arxiv.org/abs/2107.00079

و این: