Skip to content
View s-4-m-a-n's full-sized avatar
🧑‍💻
Focusing
🧑‍💻
Focusing

Highlights

  • Pro

Block or report s-4-m-a-n

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
s-4-m-a-n/README.md

LinkedIn Gmail Profile Views

📝 Solve problems not because they’re easy, but because each challenge teaches a new way to think


About

Hey! I'm Suman — an AI/ML engineer from Nepal who loves building things that actually work in the real world. I spend most of my time on computer vision and NLP, and lately I've been going deep into reinforcement learning and XR. I like research, but I also like shipping things.

👨‍💻🚫 When I'm not at my keyboard, I'm probably watching movies, playing guitar, swimming, or sending memes..


location focus learning

guitar swimming movies gym memes philosophy



Tech Stack

AI / ML  ML CV NLP PyTorch TensorFlow Keras OpenCV scikit-learn HuggingFace

Data & Visualization  NumPy Pandas Matplotlib Seaborn MLflow CVAT

Programming  Python HTML CSS JavaScript

Infra & Backend  Docker Flask Celery Redis PostgreSQL MongoDB Triton AWS Linux GitHub



Personal Projects

CV

Hands-on-Reinforcement-Learning — reinforcement learning from scratch
Aframe-tic-tac-toe — vr + RL based tic tac toe

NLP

Restaurant Chatbot — intent-driven ordering agent
Smart Auto Complete — LM-powered text completion

CV

Pain Recognition — facial expression pain detection
Autonomous Braking — vision-based POC for vehicles
Bubble Sheet Evaluator — automated OMR grading
Sketch → Photo Converter — GAN image translation

KG

Daraz Smartphone KG — product data as RDF graph

Research

SimCLR — self-supervised contrastive learning
Research Paper Summaries — 365 days of ML notes

Tools

Subtitle Downloader — CLI subtitle retrieval tool
Realtime Twitter Scraper — stream-based tweet pipeline



Engineering Interests

Computer Vision Reinforcement Learning ML Algorithms Research--driven AI ML Infrastructure Intelligent Systems



GitHub Stats

 

Pinned Loading

  1. hands-on-reinforcement-learning hands-on-reinforcement-learning Public

    Hands-on implementations of Reinforcement Learning algorithms from scratch, progressing from classical methods to deep RL with practical experiments.

    Jupyter Notebook

  2. aframe-tic-tac-toe aframe-tic-tac-toe Public

    A virtual reality Tic-Tac-Toe built with A-Frame where AI player trained using reinforcement learning compete against humans.

    Jupyter Notebook

  3. 365-days-of-ML-challenge 365-days-of-ML-challenge Public

    Welcome to the 365DaysML Challenge repository! 🚀

    Jupyter Notebook 2 1

  4. RestaurantBot RestaurantBot Public

    The Restaurant Bot is a proof of concept project powered by Rasa that aims to provide a seamless food ordering experience. With advanced natural language processing capabilities, it allows users to…

    Python 9 1

  5. smart-auto-complete smart-auto-complete Public

    enhancing Nepali News Writing with Intelligent Auto-Complete

    HTML 1

  6. autonomous_braking autonomous_braking Public

    a computer vision project that estimates distance and determine whether brake needs to be applied

    Python 1