Madhav Kanda's repositories
Blind-Image-Restoration
Pytorch based implementation of earlier State of the Art Deep Generative Filter for Motion Deblurring with integration of advanced techniques to significantly improve the results
Compiler-Project
Revolutionize Compilation: A Powerful Compiler Built from Scratch with Python, incorporating advanced techniques for lexical analysis, parsing, semantic analysis, optimization, and user-friendly interface.
AutoDiff-Inference
AutoDiff-Inference: Automatic Differentiation Inference. This Repository combines ADVI's change of variable power with Laplace Approximation to provide better inference for constrained parameters. Work done as a part of development of Bijax
MNIST-Fashion-MNIST
Compared the results obtained by using neural network with and without using MC dropout for MNIST and Fashion MNIST dataset
Assembler-Disassembler
Assembler converts assembly code into machine code. Disassembler converts machine code into assembly code.
ASTRA
"AI for Sustainability" Toolkit for Research and Analysis
bambi
BAyesian Model-Building Interface (Bambi) in Python.
bkdb
Brick Kiln DataBase
IITGn-Work
This repository contains all the assignments/submissions specific to the coursework done at IIT Gandhinagar
Mauna-Lua-CO2-Prediction
Implemented Gaussian Process and Neural Network with MC dropout to compare the result of the prediction obtained on the Mauna Lua CO2 Dataset
Non-Linear-Reparameterisation
Implemented Windowed Non-Linear Reparameterization for efficient sampling
numpyro
Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.
preliz
A tool-box for prior elicitation.