Milad Soltany
I'm an AI enthusiast with demonstrated skills in Research, Computer Vision, and Deep Learning. My area of interest includes Deep Learning, Machine Learning, and Autonomous Vehicles. I am most fascinated by generative models.
I'm an AI enthusiast with demonstrated skills in Research, Computer Vision, and Deep Learning. My area of interest includes Deep Learning, Machine Learning, and Autonomous Vehicles. I am most fascinated by generative models.
GPA: 3.67/4.0
Thesis: Design, Simulation, And Construction of An Autonomous Vehicle with Environment Perception, Planning, and Control Capabilities (Mark: 20/20)
GPA: 4.0/4.0
Authors: Milad Soltany Kadarvish, Hesam Mojtahedi, Hossein Entezari Zarch, Amirhossein Kazerouni,
Alireza Morsali, Azra Abtahi, Farokh Marvasti
Abstract: Implicit Neural Representation (INR) has recently attracted considerable attention for storing various types of signals in continuous forms. The existing INR networks require lengthy training processes and high-performance computational resources. In this paper, we propose a novel sub-optimal ensemble architecture for INR that resolves the aforementioned problems. In this architecture, the representation task is divided into several sub-tasks done by independent sub-networks. We show that the performance of the proposed ensemble INR architecture may decrease if the dimensions of sub-networks increase. Hence, it is vital to suggest an optimization algorithm to find the sub-optimal structure of the ensemble network, which is done in this paper. According to the simulation results, the proposed architecture not only has significantly fewer floating-point operations (FLOPs) and less training time, but it also has better performance in terms of Peak Signal to Noise Ratio (PSNR) compared to those of its counterparts.
I conduct research on machine learning, especially on computer vision. We are working on signal representation using machine learning (Implicit Neural Representation). Currently, I'm working on the Super-Resolution task using hyper networks.
I teach and mentor students about programming and Artificial Intelligence. AIR Center is a non-profit and student-based organization inside the Iran University of Technology
The courses we teach include:
Under the supervision of Professor Shamaghdari, I worked on multiple projects related to Computer Vision. Our work mainly consisted of optimization and 3D vision.
Some of our projects:
I have more than 3 years of experience with python programming language and various libraries required for Machine Learning tasks including NPM and my favorite library, PyTorch. Some of the libraries are listed below.
I was born in Boukan city, Iran, in 1999. Ever since I can remember, I've been in love with tech, gadgets, computers. I entered university back in 2017, majoring in Electrical Engineering. I fell in love with AI, and ever since, I've been taking part in competitions, doing projects, teaching, and loving this field.
I enjoy learning about new stuff. I'm also a huge fan of Friends and am a Marvel enthusiast.