Mohammad Taha Fakharian

من خیلی شرمنده ام که حالا دارم این رو مینویسم من حتی موتورمو رو برای پرداخت اقساطم فروختم اما کافی نبود اگر از بین محصولات من چیزی نیاز داشتید با عشق این روزها خدمت رسانی میکنیم ( اگر حمایت کنید هم دست بوستونم ⚘️) bonbooks.ir

@paraschopra 💯

Continual learning is the next big thing in AI. Today’s deep networks show catastrophic forgetting where new data points cause old knowledge to get erased because backpropagation updates all weights in a network, causing old useful info to be overwritten. Contrast this with brain - it doesn’t do backpropagation. no global updates, only local updates with each new data point. The day we have a credible alternative to backpropagation is the day we will solve continual learning. It’s an exciting time to be doing AI research!

@creet_z @tensorcore Totally worth it. 💯

@tensorcore @TheSTraveller

visited Okinawa Institute of Science and Technology. It’s in Japan, but it doesn’t feel like Japan at all. I want to be a Ph.D. student here.

Please share the arXiv homepage of a paper and NOT the PDF. Saves bandwidth, saves loading time, saves humanity.

It's wild how diverse my old-school homies have become: from great baristas to writers and athletes.

One of the best collabs I've seen lately.

@hadivafaii @NeurIPSConf I really enjoyed reading your work; it helped me a lot with understanding variational inference in the brain. I hope we can have a discussion soon in the future🤞

I will be at @NeurIPSConf Dec 2-8 to present our "Brain-like Variational Inference" paper👇 Let's connect if you enjoy first-principles thinking and brain-inspired AI 🧠🤖 Poster info: 📅 Wed, Dec 3, 11 AM — 2 PM 📍 Exhibit Hall C,D,E #500 🔗 neurips.cc/virtual/2025/l… 🧵[1/3]

در طول بیش از ۱۸۰ سال تاریخ روزنامه‌نگاری ایران و از زمان #کاغذ_اخبار میرزا صالح تا به امروز، هرگز از جایگاه خبرنگاری چنین هتک حرمتی نشده بود که این جماعت ویژه‌خوار با عمل خود و بدتر از آن طلبکاری و ادبیات سخیف خویش، به این پیشه شریف لطمه وارد ساختند‌. یاد بزرگان این وادی گرامی.

@itspapiros @Hatefna اره بفرست چک کنم.

@TheSTraveller @Hatefna خیلی مونده حاج اقا این اصلاحاتیا رو یه بررسی بکن خواستی میفرستم برات

A number of people are talking about implications of AI to schools. I spoke about some of my thoughts to a school board earlier, some highlights: 1. You will never be able to detect the use of AI in homework. Full stop. All "detectors" of AI imo don't really work, can be defeated in various ways, and are in principle doomed to fail. You have to assume that any work done outside classroom has used AI. 2. Therefore, the majority of grading has to shift to in-class work (instead of at-home assignments), in settings where teachers can physically monitor students. The students remain motivated to learn how to solve problems without AI because they know they will be evaluated without it in class later. 3. We want students to be able to use AI, it is here to stay and it is extremely powerful, but we also don't want students to be naked in the world without it. Using the calculator as an example of a historically disruptive technology, school teaches you how to do all the basic math & arithmetic so that you can in principle do it by hand, even if calculators are pervasive and greatly speed up work in practical settings. In addition, you understand what it's doing for you, so should it give you a wrong answer (e.g. you mistyped "prompt"), you should be able to notice it, gut check it, verify it in some other way, etc. The verification ability is especially important in the case of AI, which is presently a lot more fallible in a great variety of ways compared to calculators. 4. A lot of the evaluation settings remain at teacher's discretion and involve a creative design space of no tools, cheatsheets, open book, provided AI responses, direct internet/AI access, etc. TLDR the goal is that the students are proficient in the use of AI, but can also exist without it, and imo the only way to get there is to flip classes around and move the majority of testing to in class settings.

@itspapiros @Hatefna الان دیگه فک کنم باید اوکی شده باشه، فیلتر کردم. فالوورا رو هم باید یه چکی بکنم ولی یادمه اونا چون کمتر بودن همون موقعا فیلتر کرده بودم.

@itspapiros @Hatefna 🤦‍♂️

@itspapiros @Hatefna متاسفانه این اکانته رو سالای اول دانشگاه ساخته بودم و اون موقع یه سری رو برحسب ایمپرشن فالو کرده بودم. بعد مهسا خیلیاشون بلاک شدن ولی ماشالا تمومی ندارن.

@TheSTraveller @Hatefna حاجی خیلیاشونو داری یه فیلتر بزن :))

@itspapiros @Hatefna والا من اصلا نمیدونم کی فالو کردم اینا رو، سر هرداستانی گله‌ای باید انفالو کنمشون.

@Hatefna @TheSTraveller اقا این مادرقحبه هارو انفالو کن ناموسا

Walking inside a "neural computation" conference in 2025 be like: - Using LLMs to ... - LLM Agents as ... - LLM and ... P.S: I'm tired boss.

“I think recurrent loops are as crucial for intelligence as residual connections”

Two years ago, I traveled to Turkey just to take the Academic IELTS (it wasn’t available in Iran) so I could apply for a PhD. After all the challenges that have followed, from the US visa process to everything in between, I remain hopeful, seeing how far I’ve come.

Damn ranks; these devils.

Write readable code for God's sake. Feel responsible for your work.

@Rezaaishere 👎

یه جرقه دیگه بخوره میکشم زیر همه چی میرم سایت ترکیش بلیط مورد نظرو‌ میگیرم