RIML Lab – Telegram
RIML Lab
2.86K subscribers
46 photos
25 videos
7 files
144 links
Robust and Interpretable Machine Learning Lab,
Prof. Mohammad Hossein Rohban,
Sharif University of Technology

https://youtube.com/@rimllab

twitter.com/MhRohban

https://www.linkedin.com/company/robust-and-interpretable-machine-learning-lab/
Download Telegram
Media is too big
VIEW IN TELEGRAM
Reinforcement Learning Course
Dr. Rohban and Mr. Hasani
Spring 2023
Session 10
Media is too big
VIEW IN TELEGRAM
Reinforcement Learning Course
Dr. Rohban and Mr. Hasani
Spring 2023
Session 11
Media is too big
VIEW IN TELEGRAM
Reinforcement Learning Course
Dr. Rohban and Mr. Hasani
Spring 2023
Session 12
Media is too big
VIEW IN TELEGRAM
Reinforcement Learning Course
Dr. Rohban and Mr. Hasani
Spring 2023
Session 13
Media is too big
VIEW IN TELEGRAM
Reinforcement Learning Course
Dr. Rohban and Mr. Hasani
Spring 2023
Session 14
Media is too big
VIEW IN TELEGRAM
Reinforcement Learning Course
Dr. Rohban and Mr. Hasani
Spring 2023
Session 15
Media is too big
VIEW IN TELEGRAM
Reinforcement Learning Course
Dr. Rohban and Mr. Hasani
Spring 2023
Session 16
Media is too big
VIEW IN TELEGRAM
Reinforcement Learning Course
Dr. Rohban and Mr. Hasani
Spring 2023
Session 17
Media is too big
VIEW IN TELEGRAM
Reinforcement Learning Course
Dr. Rohban and Mr. Hasani
Spring 2023
Session 18
Media is too big
VIEW IN TELEGRAM
Reinforcement Learning Course
Dr. Rohban and Mr. Hasani
Spring 2023
Session 19
Media is too big
VIEW IN TELEGRAM
Reinforcement Learning Course
Dr. Rohban and Mr. Hasani
Spring 2023
Session 20
Media is too big
VIEW IN TELEGRAM
Reinforcement Learning Course
Dr. Rohban and Mr. Hasani
Spring 2023
Session 21
Media is too big
VIEW IN TELEGRAM
Reinforcement Learning Course
Dr. Rohban and Mr. Hasani
Spring 2023
Session 22
Media is too big
VIEW IN TELEGRAM
Reinforcement Learning Course
Dr. Rohban and Mr. Hasani
Spring 2023
Session 23
Media is too big
VIEW IN TELEGRAM
Reinforcement Learning Course
Dr. Rohban and Mr. Hasani
Spring 2023
Session 25
Media is too big
VIEW IN TELEGRAM
Reinforcement Learning Course
Dr. Rohban and Mr. Hasani
Spring 2023
Session 26
سلام به همه‌ی دوستان
عزیزانی که علاقه‌مند به پژوهش در حوزه یادگیری ماشین اعتمادپذیر در آزمایشگاه RIML هستند، لطفا رزومه‌ و مدت زمانی که براشون مقدور هست به پژوهش اختصاص بدهند را به ایمیل زیر ارسال کنند. نهایتاََ یک تیم از دوستان علاقه‌مند تشکیل می‌شود و یک فرآیند آموزش و در ادامه تعریف صورت مسئله برای پژوهش صورت خواهد گرفت که خروجی نهایی در قالب مقاله برای کنفرانس‌های مرتبط ML ارسال خواهد شد. بحث توصیه‌نامه برای دوستان حاضر در پروژه از سمت اساتید در نظر گرفته می‌شود.
کارهای مشابه آزمایشگاه در این حوزه را در این مقاله و این لینک می‌توانید بررسی بفرمایید.
hsirm97@gmail.com
ویدئوهای درس پردازش هوشمند تصاویر زیست-پزشکی، دکتر رهبان، پائیز ۱۴۰۲:
https://www.aparat.com/playlist/7606670

ویدئوهای درس یادگیری تقویتی، دکتر رهبان، بهار ۱۴۰۳:
https://www.aparat.com/playlist/9319081
#موقعیت_پژوهشی

سلام به همه‌ی دوستان.

قابل توجه علاقه‌مندان به پژوهش در حوزه‌ی کشف دارو (پیشبینی خواص مولکولی) با روش‌های مبتنی بر شبکه‌های عصبی عمیق، پروژه‌ای با این عنوان در آزمایشگاه RIML تعریف شده است.

پیش‌نیاز:
- تسلط کافی بر مباحث یادگیری عمیق
- آشنایی کافی با فریم‌ورک‌های یادگیری عمیق نظیر پایتورچ

موارد امتیازی:
- آشنایی با شبکه‌های عصبی گرافی
- آشنایی با مفاهیم شیمی و خواص مولکولی
- آشنایی با ابزارهایی مانند RdKit

مزایا:
- ریسرچ زیر نظر دکتر رهبان در آزمایشگاه RIML
- یادگیری مفاهیم پیشرفته در شبکه‌های عصبی گرافی و پیاده‌سازی آن‌‌ها
- ارسال پیپر در کنفرانس‌ یا ژورنال مرتبط

برای آشنایی بیشتر با این حوزه‌ی ریسرچ می‌توانید مقالات زیر را بررسی نمایید:
https://www.nature.com/articles/s41467-023-41948-6
https://arxiv.org/abs/2206.00133
https://arxiv.org/abs/2106.07971
https://arxiv.org/abs/2106.06130

در صورت تمایل، می‌توانید رزومه‌ی خود را به آیدی زیر ارسال کنید:
@aminreza_sefid
Adversarial robust learning and its generalization issues


This is a research project in the group of Dr. Rohban (RIML lab) from Sharif University of Technology

Project denoscription:
Despite deep neural networks impressive success in many real-world problems, their instability under test-time adversarial noises is the major issue against their use in safety-critical applications. Therefore, the problem of learning robust deep networks (not only accurate on original samples, but also accurate on adversarially perturbed ones) has become an active area of research.
Training the model based on the adversarial samples in each mini-batch, which is known as “Adversarial training” (AT), has been empirically established as a general and effective approach to remedy this issue. However, real challenges in practice and also theoretical aspects have remained. Especially, we face some critical generalization issues in this new learning paradigm including the larger generalization gap between test and train data in comparison with standard training or the specific phenomenon called catastrophic overfitting. Achieving a better understanding of this topic can be a good help to provide more robust models.

In this project, we aim to analyze generalization in robust learning in a more comprehensive, deep, and detailed way. The project has both theoretical and practical aspects; So having interest, capability, and perseverance in both aspects is needed.

Estimated time for the project is 6 months although it may change depending on the progress and results of the project.

For more information, you can read the following paper:
Zerograd: Costless conscious remedies for catastrophic overfitting in the FGSM adversarial training

Requirements:
- Familiarity with linear algebra fundamentals
- Familiarity with statistics and probability
- Familiarity with ML and deep learning fundamentals
- Hands-on experience in ML and deep learning
- Hands-on experience with PyTorch framework
- Dedicating considerable time and consistency to the project 
- Enthusiasm to learn and tackle research problems

Preferred qualifications:
** Familiarity with Jax framework 
* Familiarity with adversarial robustness


To apply for the position, please read the suggested paper and send your resume as well as your research interests to z.golgooni@gmail.com

We would be happy to answer any questions you may have through the above email.

#open_position
#research_application