I'm Amir a computer science researcher and programmer. I do part-time projects and will be happy to assist you in:
Amir has been highly professional, he understood the brief well, and I cannot recommend him highly enough. He's been easy to communicate with, and has helped us get a difficult project completed. Hopefully he will be able to work with me on the next phase when it happens. I would certainly ask him to work with me again.
Perfectly done! He rapidly breaks every task into pieces and delivers a compact, concise, and optimized code. He also has great knowledge in the theoretical and mathematical parts of the project. Will collaborate again.
University of Southern California, United States 2017 - 2019
Gradient Agreement as an Optimization Objective for Meta-Learning
NeurIPS Meta-Learning Workshop
This paper presents a novel optimization method for maximizing generalization over tasks in meta-learning. The goal of meta-learning is to learn a model for an agent adapting rapidly when presented with previously unseen tasks.
JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services
IEEE Transactions on Mobile Computing
In this paper, we propose an efficient, adaptive, and practical engine, JointDNN, for collaborative computation between a mobile device and cloud for deep neural networks in both inference and training phase.