Yadu Krishnan Sarathchandran, Ph.D.

Color-Compression-Unsupervised-ML

Color image compression using unsupervised Machine Learning algorithms. In this project, functions are defined to compress the images using k-means, winner takes all and Kohonen maps.

Perceptron

Perceptron is a supervised machine learning approach using binary classifiers. Here, we try to create an algorithm to create a Perceptron using Gradient Descent approach. Simple logic gate data will be used to test the accuracy of the perceptron.

Diabetes-Prediction

Developed a ML algorithm to predict/classify an unknown dataset containing the collected details of women under 21 of Pima Indian heritage, living near Phoenix, Arizona. The training data is collected from Ripley's Pattern Recognition and Neural Networks website.

Supervised-Machine-Learning-on-Normalized-Data

Some supervised machine learning algorithms are created from basic principles to study and classify a normalized synthetic data from Pattern Recognition and Neural Networks by b. D. Ripley (https://www.stats.ox.ac.uk/pub/PRNN/)

gemma-cookbook

A collection of guides and examples for the Gemma open models from Google.

Bloodraven-Chatbot

Bloodraven is an AI-powered chatbot that brings the enigmatic character from George R.R. Martin's "A Song of Ice and Fire" (ASOIAF) universe to life. Using advanced language models and Retrieval-Augmented Generation (RAG), this project creates an interactive experience for users.

Python

RAGFeynman

RAGFeynman is a question-answering assistant that leverages Retrieval-Augmented Generation (RAG) with large language models (LLMs) like Gemma or TinyLlama. This application uses a variety of tools and libraries to provide accurate and efficient answers to user queries.

sports-segementation

computer vision and sports

Python

Streamlit

This is a Streamlit-based web application that allows users to predict the species of an Iris flower based on its sepal length, sepal width, petal length, and petal width. The app uses a pre-trained machine learning model to make the predictions.