Skip to content
View AmanTewari's full-sized avatar
  • Dehradun, India

Highlights

  • Pro

Block or report AmanTewari

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
AmanTewari/README.md
Banner: Aman Tewari

Hi, I'm Aman Tewari πŸ‘‹

B.Tech Computer Science Engineering β€’ UPES, Dehradun
Backend, data & systems β€’ Always experimenting


πŸ‘¨β€πŸ’» About

I’m a Computer Science undergraduate focused on backend systems, data processing pipelines, and performance-oriented software development. I enjoy algorithmic design, system thinking, and building architectures that are clean, reliable, and scalable.

  • Currently exploring: deep learning & computer vision, smarter recommendation systems, and better ways to evaluate and deploy ML models.
  • I like working on projects where I can connect data, algorithms, and real-world usage.

πŸ› οΈ Tech Stack

  • Core languages: JavaScript (ES6+), TypeScript, Python, HTML5, CSS3
  • Backend & APIs: Node.js, Express
  • Frontend: : Bootstrap
  • Tools & platforms: Git, GitHub, VS Code, Postman, Unreal Engine 5

Tech stack icons


πŸš€ Highlighted Projects

Cross-Genre Lyrics Recommendation

Recommendation system that suggests songs across genres based on lyrics similarity and semantic relationships between words.

  • Tech: Python Β· NLP Β· embeddings Β· similarity search
  • Highlights:
    • Encodes lyrics into vector representations to compare songs across genres.
    • Experiments with different similarity metrics and preprocessing strategies.
    • Designed for exploration and discovery rather than just "more of the same".

View repository β†’


VortexSwarm

An experimental project exploring vortex/swarm-style behavior, optimization, and simulation.

  • Tech: See repository for implementation details
  • Highlights:
    • Focuses on emergent behavior from simple local rules.
    • Provides a playground for testing ideas in swarm/heuristic optimization.
    • Built to be easy to extend with new experiments.

View repository β†’


Framezz.js

Browser-based video annotation platform with interactive overlays and timeline controls, designed for fast, in-browser labeling and review.

  • Tech: JavaScript Β· HTML5 Β· CSS3
  • Highlights:
    • Overlay system for drawing and adjusting annotations on video frames.
    • Timeline controls to scrub, jump, and manage labeled segments.
    • Runs entirely in the browserβ€”no backend required for basic usage.

View repository β†’


πŸ§ͺ Learning & Experiments

  • Deep learning and computer vision (e.g., segmentation, detection, and real-world datasets).
  • Recommendation systems and evaluation strategies for ranking and similarity.
  • Designing clean, maintainable APIs and project structures.
  • Turning university lab work into reusable, well-documented repositories.

πŸŽ“ Academic & Coursework

  • B.Tech Computer Science Engineering β€” UPES, Dehradun.
  • Interests across backend development, data pipelines, and visual/pattern recognition.
  • Relevant coursework includes:
    • Algorithms & Data Structures
    • Machine Learning
    • Visual & Pattern Recognition
    • Operating Systems & Systems Programming

πŸ“Š GitHub Analytics


πŸ“¬ Contact

Pinned Loading

  1. cross-genre-lyrics-recommendation cross-genre-lyrics-recommendation Public

    AI-based music recommendation system using lyrical pattern recognition and unsupervised clustering.

    Jupyter Notebook 1

  2. VortexSwarm VortexSwarm Public

    high-performance swarm-intelligence framework for Minecraft bot coordination.

    JavaScript