Stanford Seminar — ML Explainability

If you want to be introduced into explainability topic, there is a cool seminar from Stanford! From the basics to the new horizons of research in this field.

Videos on Youtube: link
Slides: link

💻 کلاس رایگان آموزش تحلیل آماری با نرم افزار JMP

👤 مدرس: دکتر مجید ایوزیان

📆 تاریخ: چهارشنبه 25 آبان ساعت 18:30 الی 21:30
⏰  مدت زمان: 3 ساعت

🔗 لینک ثبت‌نام رایگان:
http://ctdrs.ir/cr12841

🏛 موسسه آموزش عالی آزاد توسعه
✅ با گواهینامه مورد تایید وزارت علوم، تحقیقات

Machine learning introduction دانشکده مهندسی کامپیوتر دانشگاه شریف - پائیز 1401
این دوره به تدریج در حال کامل شدن است
مدرس : دکتر شریفی زارچی آذر خلیلی


لینک ورود

Lightning AI released a new and free course - Deep Learning Fundamentals with Sebastian Raschka.

The course, as its name implies, provides an introduction to deep learning using open-source tools such as Python, PyTorch, and PyTorch Lightning, covering:
✅ Foundation of machine learning
✅ Deep learning core concepts
✅ Deep learning workflow with PyTorch/Lightning

More details are available here:
https://lightning.ai/pages/courses/deep-learning-fundamentals/

کتابچه ای که اخیرا Andrew Ng درباره ساخت رزومه و یادگیری ai و زیر مجموعه های اون به اشتراک گذاشته و در فصل های ابتدایی به بحث یادگیری نیازمندیهای این حوزه پرداخته و چالش های مختلف به نظرم بهترین مسیر و روش برای یادگیری در این حوزه شرح داده شده توصیه میکنم حتما استفاده کنید بخصوص افرادی که در ابتدای مسیر هستند 👇👇👇👇

با استفاده از سایت های زیر میتونید بدون وی پی ان از یوتیوب استفاده کنید علاوه بر اون مزیت های مثل
💢بدون تبلیغات
💢قابلیت دانلود
داره

yewtu.be/ 🇳🇱
invidious.esmailelbob.xyz/ 🇨🇦
inv.bp.projectsegfau.lt/ 🇱🇺
invidious.nerdvpn.de/ 🇩🇪
invidious.sethforprivacy.com/ 🇩🇪
invidious.tiekoetter.com/ 🇩🇪
inv.vern.cc/ 🇺🇸
Data science roadmap کانال

درباره A/B تست و روش های آماری که برای تحلیل اون میشه استفاده کرد خیلی مطلب و چیت شیت وجود داره یکی از بهترین ریسورس هایی که میتونید بهش مراجعه کنید کتاب زیره در اون مثال های واقعی زیادی از گوگل آمازون و... وجود داره که میتونید بعنوان یه رفرنس استفاده کنید

نکته مهمی که در یادگیری هرچیزی وجود داره اینه که داخل لوپ دیدن کورس ها یا کتاب های مختلف نیفتید و پروژه های مختلفی تعریف کنید و انجام بدین در لینک زیر ۲۸۵ پروژه که هم توضیح و کد داره قرارداده شده یک منبع عالی به شمار میره https://medium.com/coders-camp/230-machine-learning-projects-with-python-5d0c7abf8265

AI Research Experiences - Course Book 📚

Professor Pranav Rajpurkar released last week the materials of his course - AI Research Experiences (Harvard CS197) as an online book.

The course covers different data science tools, such as:
✅ Git, VScode, and Conda
✅ Train deep learning models with GPU on Colab and AWS
✅ PyTorch
✅ Hugging Face

https://docs.google.com/document/d/1uvAbEhbgS_M-uDMTzmOWRlYxqCkogKRXdbKYYT98ooc/edit#heading=h.o3hogvl0ayc1

یکی از بهترین منابع برای یادگیری کار با ابزارها که به تازگی منتشر شده

Meta open sourced last week a new Python package - balance 🎉. The package is handling unbalanced or biased data 🚀. Unbalanced data is a common problem in classification or survey analysis when the input data suffer from sampling bias and does not represent the overall population.

The package provides a set of tools for adjusting and visualizing biased datasets. That includes:
✅  Resample and adjust the data based on the user feedback
✅ Data visualization tools to evaluate the output
✅ Inverse propensity weighting in the form of a logistic regression model based on LASSO

License: GPL-2Resources 📚
Source code: https://github.com/facebookresearch/balance
Documentation: https://import-balance.org/
Release notes: https://import-balance.org/blog/2023/01/09/bringing-balance-to-your-data.

دوره های زیر در dataquest به مدت یک هفته رایگان شدند میتونید استفاده کنید
 
Data Scientist in Python
(Complete the first two courses in ~15 hours)
Jumpstart your career by enrolling in our most popular path. You'll begin by learning the fundamentals of Python programming for data analysis and data science. 
 
SQL Fundamentals
(Complete this full path in ~35 hours)
Add one of the most sought-after data science skills to your resume. User feedback on these courses includes statements like "Great for beginners," "the only program that has worked for me," "high retention," and "got me to interview-ready."
 
Data Engineering
(Complete the first two courses in ~10 hours)
Data Engineering roles are some of the most in demand. See if this high-paying role is right for you by completing the first two courses. It will take around 10 hours, and you'll end with a completed project.
 
Introduction to Data Analysis in Microsoft Power BI
(Complete this course in ~5 hours)
Power BI is the fastest-growing business intelligence platform. In this beginner-friendly course, you'll learn to import, load, clean, and transform data into reports and dashboards. 

1️⃣ 𝗠𝗟 𝗳𝗼𝗿 𝗕𝗲𝗴𝗶𝗻𝗻𝗲𝗿𝘀 𝗯𝘆 𝗠𝗶𝗰𝗿𝗼𝘀𝗼𝗳𝘁 (https://lnkd.in/gGcN5KGC) Learn machine learning with Microsoft’s hands-on curriculum 2️⃣ 𝗗𝗲𝗲𝗽 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗗𝗿𝗶𝘇𝘇𝗹𝗲 (https://lnkd.in/gGJJjTFN)  Find top universities’ publicly available deep learning classes 3️⃣ 𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝗰𝗲 𝗜𝗻𝘁𝗲𝗿𝘃𝗶𝗲𝘄𝘀 (https://lnkd.in/g3mUXU-r) Prepare for your upcoming interview with this repository of questions. 4️⃣ 𝗔𝘄𝗲𝘀𝗼𝗺𝗲 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 (https://lnkd.in/g-X_4miP Discover machine learning tools and resources for beginners and advanced practitioners alike 5️⃣ 𝟱𝟬𝟬 𝗠𝗟 𝗣𝗿𝗼𝗷𝗲𝗰𝘁𝘀 𝘄𝗶𝘁𝗵 𝗖𝗼𝗱𝗲 (https://lnkd.in/grSnzXNv

https://www.connectedpapers.com/

Connected Papers is a unique, visual tool to help researchers and applied scientists find and explore papers relevant to their field of work.

How does it work?
To create each graph, we analyze an order of ~50,000 papers and select the few dozen with the strongest connections to the origin paper.
In the graph, papers are arranged according to their similarity. That means that even papers that do not directly cite each other can be strongly connected and very closely positioned. Connected Papers is not a citation tree.
Our similarity metric is based on the concepts of Co-citation and Bibliographic Coupling. According to this measure, two papers that have highly overlapping citations and references are presumed to have a higher chance of treating a related subject matter.
Our algorithm then builds a Force Directed Graph to distribute the papers in a way that visually clusters similar papers together and pushes less similar papers away from each other. Upon node selection we highlight the shortest path from each node to the origin paper in similarity space.
Our database is connected to the Semantic Scholar Paper Corpus (licensed under ODC-BY). Their team has done an amazing job of compiling hundreds of millions of published papers across many scientific fields.

Note: This website is optimized for desktop browsers.