Code Monkey home page Code Monkey logo

Hi there πŸ‘‹

I'm Sepehr Rezaee, a Bachelor's student in Computer Science at the National University of Iran, Tehran. My research interests include:

  • Modeling disease progression using differential equations and employing Physics-Informed Neural Networks (PINN).
  • Developing robust and interpretable machine learning models.
  • Analyzing M/EEG data using advanced deep learning techniques.

I have submited papers in prestigious conferences like NeurIPS, focusing on topics such as backdooring out-of-distribution detection methods, scanning trojaned models, and robust novelty detection under style shifts.

My professional experience includes:

  • Research Assistant at the Artificial Intelligence and Scientific Computing Lab, Tehran.
  • Research Assistant at the Robust and Interpretable Machine Learning Lab, Sharif University of Technology, Tehran.
  • Deep Learning and Neuroscience Intern Researcher at the Institute for Research in Fundamental Sciences (IPM), Tehran.

I have received awards and honors, including the Best Ideator Award at the 7th National Young Scientists Festival and ranking among the top 0.5% in the entrance exam.

Additionally, I have served as a Teaching Assistant for Advanced Programming, Data Mining and Analysis, and Basic Programming courses at the National University of Iran. I have also been actively involved in extracurricular activities, acting as an assistant teacher and mentor for the application of Data Science and Artificial Intelligence in various industries.

Profile views

SepehrRezaee's GitHub statsTop Langs

Sepehr Rezaee's Projects

artificial-intelligence-fall-2023 icon artificial-intelligence-fall-2023

This repository is for the implementations and their reports of the projects in the course. This course held by Dr.Katanforoush in Shahid Beheshti University.

convolutional-kans icon convolutional-kans

This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing the classic linear transformation of the convolution to learnable non linear activations in each pixel.

csi icon csi

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances (NeurIPS 2020)

deep-learning-symbolic-mathematics icon deep-learning-symbolic-mathematics

Discussion and test of the first successful approach to solving symbolic mathematics problems through the use of neural networks, proposed for the first time by two Facebook researchers, Guillaume Lample and François Charton. My Master Degree Thesis in Data Science.

deepmind-research icon deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

mm-bd icon mm-bd

The implementation of the IEEE S&P 2024 paper MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    πŸ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. πŸ“ŠπŸ“ˆπŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❀️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.