شبکه داستانی عصبی – Telegram
شبکه داستانی عصبی
793 subscribers
746 photos
35 videos
96 files
1.9K links
اینجا راجع به چیزایی که دوست دارم صحبت می‌کنم: داستان، هوش مصنوعی، موسیقی، نرم‌افزار، هنر، روانشناسی و ... :)

اگه خواستید صحبت کنیم خیلی خوشحالم می‌کنید:
@alimirferdos
Download Telegram
برای اینکه بعدا بتونم به خودم یادآوری کنم:
این پیام‌ها و «هنوز»مطالعه‌کردن‌ها در حالیه که نزدیک سه چهار ساعته که به شدت گریه کردم و باز بغض دارم. So keep going
👏2
Forwarded from بریده‌های طاقچه
Awesome Diffusion Models

A fantastic and well-organized collection of learning resources on diffusion models such as introductory papers, survey papers, intro videos, long lectures, and blog posts. Papers in vision, natural language, tabular, graph, etc.

https://twitter.com/Jeande_d/status/1578482659105218560?t=SHrOg23xJxvraHToF2zxQw&s=19
Forwarded from SUT Twitter
This media is not supported in your browser
VIEW IN TELEGRAM
چقدر خوب خونده رعنا منصور آهنگ شروین رو:
#مهسا_امینی
#MahsaAmini
#Woman_Life_Freedom

◍Ped◍

@sut_tw
1
جستار جدیدی که الان نوشتم:

https://vrgl.ir/zKD6Y
👍21
AtHomeWithAI - Curated Resource List, DeepMind

A list of educational resources curated by people at DeepMind for anyone interested in learning AI, machine learning, and other related topics.

https://twitter.com/Jeande_d/status/1580641346452262913?t=yT6XOCyqOcoS4RHIO3Q4YA&s=19
این مقاله که سه چهار روز پیش منتشر شده، اثبات و بازنمایی‌ای از شبکه‌های عصبی داره و ادعا کرده که اونها رو از یک مدل black box خارج می‌کنه و تغییرپذیر (interpretable) میشن!
چیز جالبی به نظر میرسه

In this manunoscript, we show that any neural network having piece-wise linear activation functions can be represented as a decision tree. The representation is equivalence and not an approximation, thus keeping the accuracy of the neural network exactly as is. This equivalence shows that neural networks are indeed interpretable by design and makes the \textit{black-box} understanding obsolete. We share equivalent trees of some neural networks and show that besides providing interpretability, tree representation can also achieve some computational advantages. The analysis holds both for fully connected and convolutional networks, which may or may not also include skip connections and/or normalizations.

https://arxiv.org/abs/2210.05189
📣Big news!!!
Pandas DataFrame output is now available for all sklearn transformers (in dev)! This will make running pipelines on dataframes soo much easier, and provides better ways to track feature names!

🔥This is one of the biggest improvements in scikit-learn in a long time and we'd love your feedback! Please try out the nightly built and give it a go!

https://scikit-learn.org/dev/auto_examples/miscellaneous/plot_set_output.html#sphx-glr-auto-examples-miscellaneous-plot-set-output-py
1
Forwarded from Blue Phoenix
Why do I sabotage everything I love?
It's always beautiful until I fuck it up
Why do I sabotage everything I love?
The walls are closing in because I built them up
Why can't I let myself be happy? (Ooh)
Why do I gotta get in my own way? (Ooh)
My shoes are worn out, always runnin'
From the reasons that I really wanna stay