Mahmoud Nady's repositories
FMNIST_CNN
This project is a convolutional neural network (CNN) built using PyTorch that classifies images from the Fashion-MNIST dataset. The network consists of several layers including convolutional layers, pooling layers, and fully connected layers. The model achieved an accuracy of 92.1%
K_Means_From_Scratch
An implementation of the basic idea of K-Means from scratch.
Simple_Linear_Regression_From_Scratch
I have applied the fundamental idea of Linear Regression with Single Variable input. I implemented the Gradian Descent algorithm simply from scratch with no libraries such as Scikit-Learn. I just used NumPy.
SVM_Spam_Classification
This a very simple SVM Spam Emails Classification problem, I used Sklearn library to train the model and get better results
Titanic_Classification
In this challenge, I build a predictive model that answers the question: “what sorts of people were more likely to survive?” using passenger data (ie name, age, gender, socio-economic class, etc).
AboNady
Config files for my GitHub profile.
Binary_Classification_From_Scratch
A Binary Classification From Scratch, very simple algorithm to classify simple data
House_Prediction
A Kaggle's competition - The main task is to predict the prices of the houses.
Multiple_Linear_Regression_From_Scratch
A very simple Multiple Linear Regression (MLR) algorithm from Scratch. I did not use Scikit-Learn or any similar libraries
Neural_Network_From_Scratch
This is the code of a Neural Network built from scratch without any libraries other than NumPy to deal with matrices and to handle the Linear Algebra part.