Who
am I?
Mahdi Biparva
What about me?
Academic Achievements
I earned the PhD in Computer Science at York University, Toronto, Canada. I have a number of research publications in deep learning and computer vision.
work Experiences
I am a research and development engineer at Sunnybrook research institute. I have done internship during my studies. I have worked with start-up companies as a freelancer.
Software Architecture in AI
Understanding novel research achievements in one hand and developing computational programs on the other hand are the two wings of a successful R&D engineer.
Deep Learning
I have done research and development on different learning paradigms using neural networks. Convolutional networks have been in the the focus my attention.
Computer Vision
How to implement machine perception is always fascinating for me. I studied the role of visual attention on different visual tasks such as image recognition, object detection, and semantic segmentation
Programming is fun
Never stop getting tired of programming. It always feel amazing when you see the power of machines are in the hands of your coding skills.
“The mystery is in the brain information processing language. Once we learned how to decipher it, we most probably have solved intelligence.”
Who is this for?
I would passionately love to share my knowledge, expertise, skills, experiences, and techniques learned throughout all these years of study and work in this website. Magic is in sharing. If you are passionate about deep learning, computer vision, and machine learning in general, you are at the right place. This is for you!
Deep Learning Software Development
I am going to share all the coding techniques, development paradigms, and development routines that are essential for deep learning and computer vision software engineering. To have a neural network module to solve a vision task, we need to write scripts that are modular, object-oriented, readable, atomic, reproducible, and extendable.
Libraries & Packages
There are so many deep learning software libraries, packages, and modules. It is critical to know when to invent the wheel and when not to. I am going to introduce essential components for the training and inference of deep learning models. I will share programming and coding techniques, tips and tricks in the field.
Recent Posts
Presenting “Selective Network Pruning” at AISC
It is always feeling good when you get back and look at what
Presenting Video Action Transformer Network at AISC
It is always fun to read and digest research publications about action recognition
AI Development:Tools and Techniques (Part I)
Nowadays we are living in an era where we are bombarded with a
AI Development:Tools and Techniques (Part II)
AI Development: Tools and Techniques has two parts: Part I Part II This
Learning Permutation Invariant Representations using Memory Networks (AISC-CV)
There are domains in which input visual data to machine learning models are
Industrial and Academic Experiences
Would like to Get in touch?
I would be happy to hear from you. Your thoughts, ideas, comments and feedback on any aspects of the website would be kindly welcome.