Profile note

My name is Mohammad KHalooei ('محمد خالوئی' in Persian). I am an artificial intelligence researcher and also fascinated by doing scientific research in Deep learning & Big data fields of academia. And being an enthusiastic entrepreneur at the same time is interestingly intriguing.
By now, I'm a Ph.D. candidate of Amirkabir University of Technology (Tehran Polytechnic) under supervision of Prof. Mohammad Mehdi Homayounpour and Dr. Maryam Amirmazlaghani. My research field of academia is Adversarial Machine learning and Robustness of Deep Neural Networks.

International Publications

In this paper, we propose a novel self-supervised representation learning by taking advantage of a neighborhood-relational encoding (NRE) among the training data. Conventional unsupervised learning methods only focused on training deep networks to understand the primitive characteristics of the visual data, mainly to be able to reconstruct the data from a latent space. Different from the previous work, NRE aims at preserving the local neighborhood structure on the data manifold. Therefore, it is less sensitive to outliers.
( arxiv) - ( theCVF)

This research inspired by the success of generative adversarial networks for training deep models in unsupervised and semi-supervised settings, we (4 colleague) propose an end-to-end architecture for one-class classification. Our architecture is composed of two deep networks, each of which trained by competing with each other while collaborating to understand the underlying concept in the target class, and then classify the testing samples. One network works as the novelty detector, while the other supports it by enhancing the inlier samples and distorting the outliers. The intuition is that the separability of the enhanced inliers and distorted outliers is much better than deciding on the original samples. The proposed framework applies to different related applications of anomaly and outlier detection in images and videos.
( arxiv) - ( theCVF) - ( IEEE) - ( GitHub)

Experiences

Teacher Assistant of Optimization

Feb 2019 - Present
CEIT Dept, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran

Optimization is the selection of a best element (with regard to some criterion) from some set of available alternatives. Convex optimization is a subfield of mathematical optimization that studies the problem of minimizing convex functions over convex sets. Machine learning algorithms use optimization all the time. We minimize loss, or error, or maximize some kind of score functions. Gradient descent is the "hello world" optimization algorithm covered on probably any machine learning course. This course was taught by Dr. Amirmazlaghani.

CTO of the 4th AAIC competitions

March 2019
CEIT Dept, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran

AAIC is stands for Amirkabir Artificial Intelligence Competitions which was held in Tehran, IRAN. This is the forth experience which was held in Tehran and organized with one of the most technology based university of IRAN - Amirkabir University of Technology (Tehran Polytechnic). The fourth mission of AAIC competition had four leagues such as : Face recognition, Object recognition from few training examples, Stock market prediction, Persian named entity recognition and Voice command recognition field. The CEO of the forth mission of AAIC was Prof. Safabakhsh and Dr. Nickabadi.

Reviewer of Pattern Recognition Letters journal

2018 - Present
International Association of Pattern Recognition

Pattern Recognition Letters is a peer-reviewed scientific journal that is published by North Holland, an imprint of Elsevier, on behalf of the International Association for Pattern Recognition. The journal produces 16 issues per year covering research on pattern recognition. A certificate of outstanding contribution reviewer in November 2018 was awarded to me.

Teacher Assistant of Statistical Machine Learning (SML)

Sep 2018 - Feb 2019
CEIT Dept, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran

Statistical Machine Learning (SML in a brief) is a second graduate level course in advanced machine learning, assuming students have taken Machine Learning and Intermediate Statistics. This course was taught by Dr. Nickabadi.

Deep Learning Researcher

2017 - Present
Laboratory of Inteliigence and Multimedia Processing (LIMP)

Most parts of my researches is devoted to the newest Deep learning topics, and multimedia user behavior analysis.

Deep learning researcher for CoreML

August 2018
Apple IOS Foundation Program (Italy)

Core ML is the machine learning framework used across Apple products, including Siri, Camera, and QuickType. CoreML is integrated machine learning models into your app. Core ML is the foundation for domain-specific frameworks and functionality. Core ML supports Vision for image analysis, Natural Language for natural language processing, and GameplayKit for evaluating learned decision trees. Core ML itself builds on top of low-level primitives like Accelerate and BNNS, as well as Metal Performance Shaders. The machine learning stack Core ML is optimized for on-device performance, which minimizes memory footprint and power consumption. Running strictly on the device ensures the privacy of user data and guarantees that your app remains functional and responsive when a network connection is unavailable.

Machine and Vision Intelligence program participant

August 2018
International Association of Pattern Recognition (Italy)

Machine and Vision Intelligence was part of the IAPR programs and it was organized by “Computer Vision, Pattern recognition and machine Learning Italian Association” (CVPL), affiliated to International Association for Pattern Recognition (IAPR) with support of Technical Committees TC-03 (Neural Networks and Computational Intelligence) and TC-12 (Multimedia and Visual Information Systems). VSIMAC was organized by Prof. Alfredo Petrosino, Prof. Francesco Camastra and Dr. Fabio Narducci.

Industrial Deep Learning Consultor

2016 - Present
Social Collective Innovation

Most of projects have some analysis part in different data type (i.e. location, sensor, numerical, image, video and sound).

Deep Learning Researcher

2016 - Present
Big data work group of Sharif University of Technology

Most parts of my research focus is on Deep learning online courses (MOOCs) . Also, we provide the first deep learning lectures in IRAN and most of our focusable notes are from online and hot topic resources.

Big data Researcher

2015 - 2017
Big data work group of Sharif University of Technology

Most part of my research focus is on Big data online courses (MOOCs) .

Text mining researcher

2016 - 2017
Freelancing project

Sentiment analysing of WWW social commenting infrastructure.

Robotics & Artificial Intelligence

2010 - 2017
Vali-e-Asr University
  • - Qualified for participating RoboCup2017 competition at Nagoya, japan
  • - Participating in IRAN OPEN 2017 at Tehran and won 5'th prize
  • - Qualified for participating in RoboCup2016 competition at Leipzig, German
  • - Participating in IRAN OPEN 2016 at Tehran and won third prize
  • - Participating in IRAN OPEN 2015 at Tehran
  • - Participating in AUT Cup 2015 at Amirkabir university

Presentations

Machine/Deep learning

Some of my public presentation files: [I try to gather all presentation files and placed them here! (in near future :))]

Date Title, location & slides
2019 July 23 Robustness of Deep Neural Networks (Adversarial Attacks & Defenses) English slides
Amirkabir University of Technology (Tehran Polytechnic)
Audiences : Bachelor, Master and PhD students, influencer, industery internship section
Amirkabir Artificial Intelligence Summer Summit (AAIS) of SSC :: http://aaiss.ceit.aut.ac.ir
2018 Dec 6 Life of the points ('زندگی نقطه ها') Persian slides
Sharif University of Technology
Amirkabir University of Technology (Tehran Polytechnic)
Audiences : Bachelor and Master students, influencer, industery internship section
2018 Dec 23 Generative Adversarial Networks English slides
Sharif University of Technology
Audiences : Bachelor, Master and PhD students, R&D researcher of industries
2018 Aug Dense Human Pose Estimation In The Wild (DensePose) English slides
Italy, IAPR School on Machine and Vision Intelligence
Audiences : Master and PhD students, R&D researcher of industries of Italy
2018 Aug Adversarially Learned One-Class Classifier for Novelty Detection English slides
Italy, IAPR School on Machine and Vision Intelligence
Audiences : Bachelor, Master and PhD students, R&D researcher of industries
2018 Generative Adversarial Networks (application) Persian & English slides
Part Financial Information Processing Company

Audiences : Public (+ submission)
2018 Generative Adversarial Networks (definition) Persian & English slides
Part Financial Information Processing Company

Audiences : Public (+ submission)
2017 Dec Neural network visualizations Persian slides
Sharif University of Technology
Audiences : Bachelor, Master and PhD students, R&D researcher of industries, IT mans
2016 Data Analyzing with deep learning approach in bigdata stack (Deep Neural Network) Persian slides
Sharif University of Technology
Audiences : Graduated and Under-graduated student, It mans
2016 Data Analyzing with deep learning approach in bigdata stack (introduction) Persian slides
Sharif University of Technology
Audiences : Graduated and Under-graduated student, It mans

I will update this table in near future ...

Projects

Some research and industrial projects :

Improvement on Conditional WaveGAN - In this practical research we improved Conditional WaveGAN to synthesize audio samples that are conditioned on class labels. The thus synthesized raw audio is used for improving the baseline ASR system and would be better than the simple version.
Logo Generator via GAN's architecture - We implement a system that generate logo via conditional feeding. It can generate logo via our specific dataset from universities logo. We also implement this system for preferable logo generator via tagging system.
Speech Diarization by GAN's idea - This project concentrated on speaker diarization via Generative Adversarial Network and focus on discriminator partition
End-to-End Speaker diarizer - This system could used in diarization task and based on latest google SPR lab research with LSTM and some improvements.
Keyword Spotting framework - By this framework, we could detect predefined persian/any language words for sending request in Internet of Things api's.
Latent space feature learning - Most influence of this project, is focused on generative posterior structure of generator in generative adversarial networks like DCGAN, WGAN etc.
Dominant rare event detection - By this experience, we could detect rare event detection via deep learning approaches like Generative Adversarial Network in acceptable performance.
Bank data mining - This project is focused on implement credit scoring system for analysing customer in bank.
Innovation Panel - A responsive saving infrastructure and framework for innovation communities.
Robot Operation System - We (VRU robotic center) want to improve our manipulation and also artificial intelligence system in real rescue league at IRANOPEN and also Nagoya,Japan international RoboCup competition (2017).
Motion detector - We (VRU robotic center - about 3 colleagues in a different department like electrical engineering, mechanical engineering) want to have artificial intelligence system in real rescue league at IRANOPEN and also Leipzig, German international RoboCup competition (2016). In this project, I had an opportunity to implement artificial intelligence level of VRU robot (Hurtash) and being the pioneer of the southeast robotic team of our country (KERMAN).
Farda automation - We (about 6 colleague) implement cultural automation system for manipulating data in different platform and usages. In this project, I have DBA manager task and also be in developer part of Dynamic menu loader of backend and UI.

Skills & Proficiency

Deep learning topics (for lecture, ...)

Deep learning frameworks (Tensorflow, Keras, Pytorch, ...)

Big data analysing frameworks (Mahout, Apache spark)

Front-end developer

Back-end developer

Network skills

Graphical skills

Last update 2018