Skip to content
View Dhruvbitmesra's full-sized avatar

Highlights

  • Pro

Block or report Dhruvbitmesra

Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
Dhruvbitmesra/README.md

Typing SVG

A Quantitative Economics and Data Science student at BIT Mesra, diving deep into Machine Learning, Deep Learning, GenAI, LLMs, and Data Analytics. I love building smart things that make data come alive.

๐Ÿ“ง Email Me ๐Ÿ‘‰ โœ‰๏ธ dhruvjordan610@gmail.com ๐Ÿ˜Š๐Ÿ˜Š

  • ๐ŸŒฑ Iโ€™m currently learning: GenAI, AgenticAI, MCP
  • ๐Ÿ˜„ Pronouns: Kinshu
  • โšก Fun fact: I talk to AI so much, it might just start calling me its dataset.

๐ŸŒ Socials:

Instagram email



๐Ÿ’ป Tech Stack:

Python R AWS Heroku Apache Airflow MySQL TensorFlow Scipy MongoDB Docker AWS MySQL Power Bi Grafana Heroku Flask Git GitHub Actions GitHub Matplotlib mlflow NumPy Pandas scikit-learn Kubernetes


๐Ÿ“Š GitHub Stats:




๐Ÿ’ก Fun Neural Network & ML Facts

  • The first neural network, Perceptron, was introduced in 1958 by Frank Rosenblatt.
  • Deep learning networks are inspired by the human brain, using layers of interconnected โ€œneuronsโ€.
  • Convolutional Neural Networks (CNNs) are the backbone of image recognition and computer vision.
  • Neural networks learn by adjusting weights using backpropagation and gradient descent.
  • GPT models have billions of parameters, making them capable of generating human-like text!
  • Overfitting is like memorizing your homework answers instead of understanding concepts โ€” common in small datasets!

๐Ÿ” Top Contributed Repo


Pinned Loading

  1. TwinQueryClassifier-App TwinQueryClassifier-App Public

    An intelligent NLP-driven model that flags semantically similar questions using fuzzy matching and ML, presented through a clean, modern Streamlit UI.

    Python

  2. Deep-learning-concepts-learning-phase- Deep-learning-concepts-learning-phase- Public

    A concise, beginner-friendly repository covering essential deep learning concepts, architectures, and training techniques for quick reference and revision.

    Jupyter Notebook

  3. Multimodal-Game-Recommendation-System Multimodal-Game-Recommendation-System Public

    ๐ŸŽฎ Multimodal, content-based game recommendation system using BERT, ResNet50, and CLIP โ€” built for cold-start scenarios and deployed with Streamlit.

    Jupyter Notebook

  4. Taxi-Trip-Data-Analysis-SQL-Project- Taxi-Trip-Data-Analysis-SQL-Project- Public

    This project showcases SQL-driven analysis of NYC Taxi Trip data, focusing on data cleaning, exploration, and business insights. It examines revenue trends, driver performance, route efficiency, anโ€ฆ