Subramanya Nagabhushanaradhya's Projects
arxiv-sanity lite: tag arxiv papers of interest get recommendations of similar papers in a nice UI using SVMs over tfidf feature vectors based on paper abstracts.
An experimental open-source attempt to make GPT-4 fully autonomous.
Autofill, simply install the extension and create a profile with all of your relevant information. When you come across a job application, click the extension icon and click "Autofill". The extension will fill majority of your fields leaving behind only job specific fields.
A curated list of awesome Machine Learning frameworks, libraries and software.
A curated list of awesome READMEs
Cryptocurrency Price Prediction Using LSTM neural network
Medical record management system.
download_echo360 is a command-line Python tool that allows you to download lecture videos from any university's Echo360 system.
experimenting with egocentric
Flappy Bird using NEAT.
Forex Pairs pattern recognition and prediction using tick data.
Image Noise Reduction with Auto-encoders using TensorFlow
3D file importer to UE4 project at runtime using Assimp and Procedural Mesh
The smooth transition among panorama views. By providing control point correspondences, we can guide the view morphing from one panorama to another in a natural way. Compared with typical solutions like bending, stretching, and parallax-effect methods, this solution provides a natural transition effect similar to what people see when walking in a 3D environment from one panorama viewing site to another.
Its a prototype for map viewer which can be modified to integrated with any IPS system inside warehouse to navigate to get invetory from current location to counter or end location.
LLM infrastructure for developers
Transfer learning in estimating depth from low light or monochrome grayscale images using a standard encoder-decoder architecture.
Meta Trader 4 : Indicators
"Navigating UMass Amherst: A Handbook for International Students" is more than just a guide; it's a friendly companion designed to make the transition to UMass Amherst as smooth and enjoyable as possible. Equip yourself with this book, and step confidently into your new adventure.
trying out NER classifier
We propose to use a mode that favors sentiment understanding and empathetic response generation using the sentiment of each dialogue context. It is based on the Text-to-Text Transformer (T5) and we extend it with a sentiment analysis model and weighted loss during training.
Random fun Repo for random scripts and notebooks.
Apply of random walk algorithm.
Notebooks and various random fun