Name: Roshan Ram
Type: User
Company: Carnegie Mellon University
Bio: carnegie mellon grad | information systems, machine learning, software engineering
Location: Princeton // Pittsburgh
Blog: linkedin.com/in/roshanr11
Roshan Ram's Projects
Python SDK for agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks like CrewAI, Langchain, and Autogen
Capstone project for Udacity's Machine Learning Engineer Nanodegree and a submission to Kaggle's Allstate Severity Claims competition.
In this project, I build, train, validate, and test a neural network from scratch using the popular Bike-Sharing dataset to predict daily bike rental ridership.
Predicting housing prices using machine learning and the widely available Boston Housing dataset.
A user-friendly tutorial to acquaint CMU students to the Andrew File System.
A predictive platform for stock market prediction, utilizing shallow machine learning algorithms built from scratch such as SLR and MSLR, as well as deep learning methods such as LSTMs + RNNs built with Keras.
A sidescrolling game in which the goal is for you, Flappy, to consume a certain number of blobs within a given amount of time. (Based on CMU's 15-112 Graphics Package [0.8.5])
This repository is the base repository that students will fork and use for the git / github recitation
Code for the habitat challenge
Used deep learning to train a CNN + RNN/LSTM on the MS-COCO dataset to automatically generate captions.
Dataset and evaluation script used for depednency parsing in Sanskrit
The website for the CMU Language Technologies Institute low resource NLP bootcamp 2020
Fork of Mayan: Free Open Source Document Management System, for use in CMU 17-313
A new lightweight auto-differentation library that directly builds on numpy. Used as a homework for CMU 11785/11685/11485.
Natural language processing part-of-speech (POS) tagger created with the Pomegranate library and Keras using Hidden Markov Models.