Hi there

I'm Moslem Yazdanpanah

AI Enthusiastic {Fast, Deep, Active} Learner Design Thinker

About Me


I am a machine learning engineer with a research background, having skills in Python, Neural Networks and academic research. I hold a Master's degree in AI and Robotics from University of Kurdistan and looking to solve interesting problems as simply and elegantly as possible

Skills

Here are a few cool things about me


My Soul

A child-minded creative introvert, like never get tired of learning. I always deep dive to new concepts but, spine-up and surpass others by connecting connecting ideas and empathic view point. Ethic and morality has and also makes a lot of meaning and sense to me.

ML Ecosystem

Python, more than just a tool, it is a mindset of thinking and living! Pytorch, and any related tools and libraries needed to be a good ML engineer. A last but not the least, the ML knowledge which empowered all of us and these tools towards understanding a new universe!

Design Thinking

The last frontier of human being in front of intelligent machines. What sees the world as a whole, interconnect components, and give existence to systems. Design bridges the gap between problem and solutions in a manageable way. The more comprehensive, the more ROI.

Things I've done

Here are a few cool things about me


Revisiting Learnable Affines for Batch Norm in Few-Shot Transfer Learning

Batch Normalization is a staple of computer vision models, including those employed in few-shot learning. Batch Normalization layers in convolutional neural networks are composed of a normalization step, followed by a shift and scale of these ....Project page

Visual Domain Bridge: A Source-Free Domain Adaptation for Cross-Domain Few-Shot Learning

Due to the covariate shift, deep neural networks performance always degrades when applied to novel domains. In order to mitigate this problem, domain adaptation techniques require samples from target data during the feature extraction training, .... Project page

Shift and Scale is Detrimental To Few-Shot Transfer

Batch normalization is a common component in computer vision models, including ones typically used for few-shot learning. Batch normalization applied in convolutional networks consists of a normalization step, followed by the application .... Project Page

Industry Experiments

A 10 years journey From back-end and front-end development to system design escalated my mindset like you never could touche in academia. For more information view my Linkedin profile