Pranav-Taneja
MLE @ Krutrim | Ex Compiler Engineering @ AMD | CS Grad @ BITS Pilani
Patiala, Punjab, India
Pinned Repositories
basic-GAN-MATLAB
This repository holds the source code to a very simple GAN implemented in MATLAB to generate a 4-pixel pattern. The primary purpose is educational so that one can understand the flow of data and cost function optimisation to understand working of a GAN better.
compiler
Kaun-Banega-Crorepati-KBC-game
A command line interface game based on the popular TV show Kaun Banega Crorepati (KBC) written entirely in C
llvm-project
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. Note: the repository does not accept github pull requests at this moment. Please submit your patches at http://reviews.llvm.org.
Marks-Predictor
# Score-Predictor A simple project which predicts student's score in exam. Linear Regression is used to train the model. Label encoding is also done to encode categorical data. 32 Features are used to predict marks. The data set is taken from UCI Machine Learning Repository. Flask is used to integrate the machine learning model with the webpage. The root mean square error is 1.19.
compiler
Pranav-Taneja's Repositories
Pranav-Taneja/basic-GAN-MATLAB
This repository holds the source code to a very simple GAN implemented in MATLAB to generate a 4-pixel pattern. The primary purpose is educational so that one can understand the flow of data and cost function optimisation to understand working of a GAN better.
Pranav-Taneja/compiler
Pranav-Taneja/Kaun-Banega-Crorepati-KBC-game
A command line interface game based on the popular TV show Kaun Banega Crorepati (KBC) written entirely in C
Pranav-Taneja/llvm-project
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. Note: the repository does not accept github pull requests at this moment. Please submit your patches at http://reviews.llvm.org.
Pranav-Taneja/Marks-Predictor
# Score-Predictor A simple project which predicts student's score in exam. Linear Regression is used to train the model. Label encoding is also done to encode categorical data. 32 Features are used to predict marks. The data set is taken from UCI Machine Learning Repository. Flask is used to integrate the machine learning model with the webpage. The root mean square error is 1.19.