The Cerebros package is an ultra-precise Neural Architecture Search (NAS) / AutoML that is intended to much more closely mimic biological neurons than conventional neural network architecture strategies.

PyTorch implementations of the beta divergence loss.

Super Resolution's the images by 3x using CNN

Implementation of two new protocols in the Shuffle Model of Differential Privacy for the private summation of vector-valued messages

Program for non-planar camera calibration, mean square error, RANSAC algorithm, and testing with & without noisy data using extracted 3D world and 2D image feature points.

Comparison of common loss functions in PyTorch using MNIST dataset

Classifying whether the credit card transaction is fraudulent or not using Logistic Regression

A Mathematical Intuition behind Linear Regression Algorithm

This repo houses a Jupyter Notebook which is intended to walk you through Gradient Descent Algorithm from scratch.

Learning Project ML - Diabetes Prediction

The objective is to analyze flight delays in the United States. Data from airlines, airports, and runways will be collected and processed. Machine learning models will be built using logistic regression, decision trees, and XGB classifiers. Visualizations will be created in Tableau, and Excel dashboards and SQL queries will be used for analysis.

Applied Multivariable Linear Regression on Iris Dataset

Implementation of different optimization algorithms. This was done as a research project for the MSc. in Computer Engineering.

Value to Business :: Using this Regression model, the decision-makers will able to understand the properties of various products and stores which play an important and key role in optimizing the Marketing efforts and results in increased sales.

Used cars price prediction over custom dataset using simple linear regression

Python images vector quantizer lossy compressor and decompressor.

This repository utilizes time series analysis to predict natural gas prices, aiding informed decisions in the energy market. Through meticulous data preprocessing, visualization, and ARIMA modeling, it provides accurate forecasts. With regression and interpolation techniques, it offers deeper insights for stakeholders, enabling proactive strategies

This Repository contains scratch implementations of the famous metrics used to evaluate machine learning models.