Skip to content
View reybahl's full-sized avatar

Highlights

  • Pro

Organizations

@yaledailynews @Y-Hack @coursetable @GLHS-AI-Machine-Learning

Block or report reybahl

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, 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
reybahl/README.md

Hi there 👋

I'm Reyansh, a student at Yale University studying computer science and data science. I'm a machine learning researcher and software developer. My interests include natural language processing (NLP), computer vision, remote sensing, signal processing, deep learning, web development, and app development.

Machine Learning Projects

  • Assistant: A machine learning powered, voice-based virtual assistant for Raspberry Pi. Supports several features like conversation, weather, opening websites, geolocation, date/time, and creating timers.
  • SOC Mapper and Predictor: Using machine learning to analyze remote sensing imagery from NASA's Landsat 8 satellite to monitor and predict soil organic carbon and help facilitate regenerative agriculture, improve soil carbon sequestration, and fight climate change.
  • SciQALM: Science Question Answering Language Model -- Retrieval-Augmented Generation (RAG) with Zephyr 7B β model, all-MiniLM-L6-v2, and MongoDB Atlas Vector Search for scientific question answering based on arXiv papers
  • RSS time-series classification: Using machine learning to classify time series of radio signal strength (RSS) between nodes of a Wireless Sensor Network (WSN). This is used to predict the pattern of user movements in real-world office environments and has applications in ambient assisted living.
  • Argumentative Element Identification: Using token classification to determine distinct argumentative elements, including claim, evidence, etc. Used Longformer (Long-Document Transformer) model for token classification.
  • Kaggle Notebooks: I'm ranked an expert on Kaggle and have published 18+ notebooks detailing my approaches to various real-world problems using machine learning.

Other Projects/Repositories

Skills

My Skills

Pinned Loading

  1. Assistant Assistant Public

    A machine learning powered, voice-based virtual assistant for Raspberry Pi. Supports several features like conversation, weather, opening websites, geolocation, date/time, and creating timers.

    Python 31 11

  2. Argumentative-Element-Identification Argumentative-Element-Identification Public

    Given an essay, this project uses machine learning and token classification to separate the essay into distinct argumentative elements (eg. Claim, Evidence, Counterclaim, etc.)

    Python 1

  3. NoteTaker NoteTaker Public

    note taking app with angular.js frontend, node.js/express.js backend, mongodb database

    TypeScript 1

  4. Chess-Game Chess-Game Public

    A full chess game implementation (with GUI) in Java.

    Java 2 1

  5. Movement-Prediction-Time-Series Movement-Prediction-Time-Series Public

    Predicting user movements using time series classification of radio signal strength (RSS) data

    Jupyter Notebook 3

  6. SciQALM SciQALM Public

    Retrieval-Augmented Generation (RAG) w/ Zephyr 7B β & Atlas Vector Search for scientific question answering based on arXiv papers

    Python 1