G K

Research Scientist at Johannes Kepler University Linz

Austria, India
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
G K is a research scientist and deep learning researcher with 13 years of experience, currently based in Austria with origins in India. He specializes in neural network architectures and practical DL implementations, demonstrated by contributions to a well-scoped tutorial on self-normalizing networks (SNNs) applying SELU activations, SNN-tailored dropout, and input scaling for CNNs on MNIST. Comfortable in TensorFlow, he designs model architectures, training pipelines, and conducts experiments end-to-end to validate ideas. His profile blends academic-style research rigor with hands-on engineering, making experimental results reproducible and usable for practitioners. Beyond coding, he shows a knack for demystifying niche techniques—translating theoretical SNN properties into concrete, tested implementations.
code13 years of coding experience
github-logo-circle

Github Skills (8)

mask-rcnn10
faster-rcnn10
machine-learning10
tensorflow10
python10
mnist10
data-analysis9
keras9

Programming languages (4)

C++RJupyter NotebookPython

Github contributions (5)

github-logo-circle
bioinf-jku/SNNs

Jun 2017 - May 2020

Tutorials and implementations for "Self-normalizing networks"
Role in this project:
userData Scientist
Contributions:32 commits, 1 PR, 28 pushes in 2 years 11 months
Contributions summary:G primarily contributed to a tutorial on self-normalizing networks (SNNs) applied to the MNIST dataset, specifically focusing on convolutional neural networks (CNNs). They implemented SELU activation functions, dropout variations tailored for SNNs, and input scaling. Their work involved defining model architectures and training procedures within a TensorFlow environment. They also performed experiments and reported results.
pytorchimplementationsloss-functionsdeep-learningnormalizing
Large-scale ligand-based virtual screening for potential SARS-Cov-2 inhibitors using a deep neural network
Contributions:22 commits, 22 pushes in 11 days
screeningdeep-learningdeep-neural-networkscalelarge-scale
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial
G K - Research Scientist at Johannes Kepler University Linz