Skip to content
View aniketmishr's full-sized avatar
1 follower · 10 following

Highlights

  • Pro

Block or report aniketmishr

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
aniketmishr/README.md

👋 Hi, I'm Aniket Mishra

🎓 B.Tech. in Artificial Intelligence and Data Science
📧 aniketmishra3476@gmail.com
🔗 LinkedIn | GitHub

💡 About Me

I'm passionate about Applied AI Research, particularly at the intersection of Computer Vision and Natural Language Processing. My goal is to bridge the gap between cutting-edge deep learning research and practical, impactful solutions. I love reading research papers, building models from scratch, and deploying intelligent systems that solve real-world problems.

🔧 Tech Stack

  • Languages: Python, C, C++, Kotlin, SQL
  • AI/ML: PyTorch, Transformers, NumPy, Pandas, LangChain
  • Frontend: Streamlit, Jetpack Compose, PyQt5
  • Tools: Docker, Git & GitHub

🚀 Featured Projects

🩺 FundusAI

Explainable Fundus Disease Detection Web App
🔬 EfficientNet-B3 model with Grad-CAM visualizations (98% accuracy)
🌐 FastAPI backend + Bootstrap frontend + Dockerized deployment
🖼️ Upload multiple retinal images and get instant disease predictions (AMD, Cataract, Diabetic, Normal)

🧠 PaliGemma

Building a Vision-Language Model from Scratch
🧩 Integrated SigLIP (image encoder) and Gemma (language model)
📖 Reproduced architecture to understand multimodal learning systems
🧪 Inspired by Google's PaliGemma research for vision-language tasks

✏️ NeuroDoodle

Real-time Doodle Classification Web App
🖌️ Users draw on a virtual canvas, app predicts what was drawn
📦 Vision Transformer fine-tuned on Quick, Draw! dataset
🚀 Built using Streamlit for rapid, interactive deployment

🧱 Deep Learning from Scratch

Re-implementing DL architectures from the ground up
🧠 Rebuilt LLaMA, ViT, Transformer Encoder-Decoder, CLIP, and more
📜 Faithfully follows the original papers and architectural specs
🎯 Focused on gaining intuition and low-level understanding

🏥 CureCub

🏆 1st Prize Winner at College Hackathon
💊 Built a smart healthcare platform prototype to streamline diagnosis
🛠️ Combined frontend and AI to demonstrate a real-world healthcare use case

📘 Education

Bachelor of Technology (B.Tech)
Artificial Intelligence and Data Science
C.T.A.E. Udaipur (2023–2027)

📈 Let's Collaborate!

I'm always open to exciting collaborations in:

  • Vision-Language research
  • Open-source deep learning
  • Model interpretability and XAI
  • Educational AI tools

Feel free to reach out or connect!

Popular repositories Loading

  1. cure-cub cure-cub Public

    Kotlin 4

  2. connect-app connect-app Public

    Connect is your ultimate contact management app, designed to streamline your connections with ease.

    Kotlin 2

  3. ascii-rotating-shapes ascii-rotating-shapes Public

    An interactive ASCII art project showcasing a rotating, colored 3D cube in the terminal, inspired by Andy Sloane's rotating donut.

    C++ 2 1

  4. extract-ai extract-ai Public

    ExtractAI is an Android application built using Jetpack Compose that allows users to extract text from images using Optical Character Recognition (OCR).

    Kotlin 1 1

  5. DeepLearning-From-Scratch DeepLearning-From-Scratch Public

    This repository contains implementations of famous deep learning architectures built from scratch

    Python 1

  6. pocket-agent pocket-agent Public

    Pocket Agent is your personal AI assistant on Telegram. It can answer your quick questions, help with complex tasks, and even manage daily routines, all from your pocket.

    Python 1