Education
Ph.D. in Computer‌ Science                Oct 2018 - Nov 2022
M.Sc. in Artificial Intelligence                2013 - March 2016
GPA: 18.7/20 - Ranked 3rd
B.Sc. in Computer Engineering             2007 - 2011
GPA: 16.50/20 - Ranked 4th
Summer Schools
Machine Learning Summer School 2019(MLSS)             July 2019
Projects
  Upper Confidence Reinforcement Learning exploiting state-action equivalence (M.Sc. Internship)
  Distributed Multi-task Learning (M.Sc. Thesis)
We have solved the optimization problem of Multi-task learning in a distributed fasion while
including the theoretical analysis of extending the framework on Policy Gradient Reinforcement
Learning problems. We have reduced the convergence time of the algorithm and the memory consumption
of each agent which makes this approach suitable for big data problems.
  Online Face Recognition and Tracking
We have developed an online face recognition software. After some preprocessing(illumination
reduction and alignmenting the face) on each image of the video stream, we extract discriminative
features and train a generative model so as to recognize the identity of passing individuals. Our approach is
fast enough to be used for online processing.
  Facial Expression Detection
Our goal was to guess human emotions using facial expressions. To do so, we employed image
processing techniques to extract initial features and used epsilon-SVR to transfer them into
a more discriminative space. Using these features, a model for facial emotion detection has
been constructed by SVM that returns the probability of each emotion category.
  Predicting Excitement for DonorsChoose.org -
(KDD Cup 2014) - Top 25%
Given projects' information from DonorsChoose.org, the goal of this project is
to predict how exciting each project is. Using data mining techniques, we extracted relevant
and discriminative features from the raw information. Several sampling methods have been
investigated to overcome the imbalanced dataset problem. Finally, different methods for learning
the output value (Project's excitement prediction) such as random forest, naive bayes, etc.
have been applied to complete the model.
  Malware Detection using XCS
The goal of this project was to distinguish malicious and benign binary files. We proposed
two ideas to solve this problem:
1. ``XCS (RL-based Genetic Algorithm)'' and,
2. ``N-gram based feature weighting using Genetic Algorithm''.
  Fuzzy Rule-Based Classification System
In this project we want to learn the rule weigths of a fuzzy rule based classification system.
To do so, a three-steps greedy simulated annealing-based idea have been applied in order to
learn the weight of each of the rules. This approach is fast and efficient as it reduces the
number of rules required.
  Behavior-Selection by Emotions and Cognition in a Multi-Goal Robot Task (B.Sc. Project)
The goal of this project is to design a learning agent that finds a policy to live longer while
encountering conflicting situations. Therefore, I have implemented a reinforcement learning-based
agent who maintains high performance while satisfying conflicting goals.
Honors and Awards
- 2019 - Best Student Paper Award at ACML 2019
- 2019 - Accommodation Scholarship for MLSS 2019
- 2018 - Full Scholarship to attend TMLSS 2018
- 2018 - Best Poster award at TMLSS 2018
- 2016 - Ranked 3rd among Artificial Intelligence Major Students at Shiraz University.
- 2014 - Among Top 2% participants of Iranian PhD Entrance Exam - Artificial Intelligence
- 16th Iran National Collegiate Olympiad in Computer Engineering[Here]: 2012 - Awarded by Shiraz University's office of Exceptional Talented Students[Here] 2011 - 13th Place in the final round among 9 regions' tops 2011 - 2nd Place in the 6th region's competiton
- ACM-ICPC - (Scintillants → RSM Team)[Here]: 2010 - 10th Place, Asia Region Competitions, Sharif University, Tehran, Iran (90 Teams)[Here]
- 2020 Sep - Talk on Programming, Shiraz University
- 2019 Jun - Talk on Academia Abroad, Shiraz University
- Teaching Assistant - Shiraz University:
- Advanced Machine Learning: Spring 2015
- Machine Learning: Fall 2014.
- Artificial Intelligence: Spring 2014, Fall 2013, 2010.
- Algorithm Design: Spring 2011.
- Discrete Mathematics: Spring 2010, 2009, Fall 2008.
- Fundamentals of Programming: Fall 2010, 2009.
- Lecturer:
- 2018 - 2022 - Inria Lille - Nord Europe, Magnet team, PhD Researcher (3 years and 6 months)
- 2017 - Inria Lille - Nord Europe, SequeL team, Research internship (4 months).
- 2016 - Shiraz University Center of Intelligent Vision and Image Processing (6 months).
- 2014 - 2016 - Shiraz University Machine Learning Lab
- 2013 - 2014 - Shiraz University Image processing and Vision lab
- 2016 - AIESEC Shiraz team member
- 2015 - 2016 - Shiraz University "Future Team"
- 2008 - 2012 - ACM student membership
- 2007 - 2011 - Shiraz University ACM association
- 2007 - 2009 - Computer Department's "Students' Scientific Council"
- 2016 - AIESEC, Team Member
- 2016 - TEDxShirazUniversity:
- Organizing committee Member
- Content Management & Media team Member - 2015 - Winter - "Hour of Code" for elementary school students
- Organizing Committee Member - 2014 - Fall - Weekly presentations of AI    We presented various topics: Natural Language Processing, Reinforcement Learning, Optimization, etc.
- 2009 - "University Open Day program"
- Student chair of Computer Department
:= Our Team/I have been the initiator.
Email Me
myname mylastname inria fr {with [at] in the second, and [dot] in left spaces}
Publication
- 2022 - Identifying structure in online and collaborative learning problems PhD Thesis M. Asadi.
- 2022 - Collaborative Algorithms for Online Personalized Mean Estimation TMLR 2022, M. Asadi, A. Bellet, O-A. Maillard, M. Tommasi.
- 2019 - Model-Based Reinforcement Learning Exploiting State-Action Equivalence ACML 2019, Proceeding of Machine Learning Research M. Asadi, S. Talebi, H. Bourel, O. Maillard.