DhruvSrikanth

GoLLUM

A compiler for GoLite, a simple mix between Go and C/C++. The compiler uses LLVM for its IR representation and is designed for an ARM64 backend architecture.

mlx-graphs

Graph Neural Network library made for Apple Silicon

Unix-Like-Shell

A pure C implementation of a Unix-like system emulating the Bourne Again SHell.

CUDANN

A distributed implementation of a deep learning framework in CUDA.

DenoisingDiffusionProbabilisticModels

An implementation of Denoising Diffusion Probabilistic Models (DDPMS) with experiments on different beta schedulers.

Boosting-Theory

A collection of papers produced on the theory of boosting as applied to binary classification. Further extensions to the multi-class classification problem and necessary and sufficient conditions to ensure boostability i.e. weak learning conditions. Finally, an overview over boosting algorithms and models employed in industry.

clrs

Consult the DeepMind clrs repository for the description.

ConditionalGAN

Simulate experiments with the Conditional GAN architecture and training algorithm in PyTorch using this package.

DCGAN

FastConv

Distributed and serial implementations of the 2D Convolution operation in c++ and CUDA.

ML-Templates

Templates for AI projects.

mlx

MLX: An array framework for Apple silicon

project-template

A template for anyone interested in engaging in technical projects involving code.

PSNRGAN

pynn

Purely NumPy based API for building deep neural networks.

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

tsfresh

Automatic extraction of relevant features from time series:

VanillaGAN

Simulate experiments with the Vanilla GAN architecture and training algorithm in PyTorch using this package.

DhruvSrikanth

DhruvSrikanth.github.io

Frozen-Lake-Q-Learning

A reinforcement learning-based approach playing the frozen lake game from openai-gym.

lightning

Deep learning framework to train, deploy, and ship AI products Lightning fast.

MapReduceSparseSolver

An Go native implementation of the Map Reduce parallel framework for a sparse linear solver utilizing conjugate gradient to solve the Poisson equation.

Numerical-Optimization-Techniques

A collection of numerical optimization techniques I've implemented to better my understanding of them.

PipelineBSPImageEditor

An image editor implemented in Go, utilizing the pipeline and BSP parallelism schemes.

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

SupContrast

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

TicTacToeAI

TwitterGo

A parallelized twitter application implemented with a producer consumer model and lock free queue in Go.

WorkBalancingStealingImageEditor

An image editor implemented using the work balancing and work stealing parallelism schemes in Go.