Satvik Varshney 's repositories
PDFSuno
Converts English PDFs/Ebooks into Hindi audiobooks using NLP, TTS, Cloud technologies, enhancing content accessibility for educational purposes in underprivileged areas with poor education rates
GenAI-EvenMNIST
GenAI-EvenMNIST harnesses generative AI through a Variational Auto-Encoder (VAE) with convolutional layers to generate even-digit images from the MNIST dataset. This project showcases the application of AI for image creation and deep learning
IsingModelBoltzmannMachine
Using Monte-Carlo simulated datasets, a completely transparent Boltzmann Machine trained on 1-D Ising chain data is implemented to predict model couplers in the absence of past coupler values. Methods from machine learning applied to theoretical physics are on display in this work.
BitWiseLearner
An innovative project utilizing Recurrent Neural Networks (RNNs) to perform multiplication on binary integers. This repository showcases how deep learning can understand and execute fundamental arithmetic operations on binary data, offering insights and methodologies for similar tasks.
MultiLabelClassifierPyTorch
This PyTorch project sorts even MNIST numbers into groups. It shows how to train a neural network with hyperparameters that can be set in JSON, prepare data, and test its performance. It shows how to add data, check the accuracy of the model, and see the loss.
LinearRegressionFromScratch
An investigation of basic linear regression that contrasts gradient descent with analytical answers. shows off fundamental machine learning algorithms on fictitious datasets for learining purposes.
Deep-Learning-for-Spacetime-Classification
This project applies machine learning techniques to the classification of spacetimes in the context of general relativity, specifically addressing the Petrov classification of the Weyl tensor