Abdelrahman-Amen

Abdelrahman-Amen

Applying-different-unsupervised-learning-techniques

Applying various clustering techniques to the dataset, and my primary goal is to identify and choose the most effective method that best captures the underlying patterns in the data.

Applying-Kfold-From-Scratch

Applying_One_Versus_All_technique_and_use_Minimum_Sum_Squared_Error_MSSE

Building-Neural_Network

Car_Plate_Detection_using_YOLOv8

Centroid-in-Pattern_Recognition

This repository implements centroid-based pattern recognition, extracting features from images using grid cell centroids for classification in computer vision and image processing.

Chain-code-in-patter-recognition

Cifar10_Using_Convolutional_Neural_Network

Web_Scraping-and-Text_Processing-NLP

Web scraping involves extracting data from websites. Text processing techniques like tokenization, stemming, lemmatization, and removing stopwords refine raw text for analysis.

Abdelrahman-Amen/Web_Scraping-and-Text_Processing-NLP

Web scraping involves extracting data from websites. Text processing techniques like tokenization, stemming, lemmatization, and removing stopwords refine raw text for analysis.

Abdelrahman-Amen/Abdelrahman-Amen

Abdelrahman-Amen/Applying-different-unsupervised-learning-techniques

Applying various clustering techniques to the dataset, and my primary goal is to identify and choose the most effective method that best captures the underlying patterns in the data.

Abdelrahman-Amen/Applying_One_Versus_All_technique_and_use_Minimum_Sum_Squared_Error_MSSE

Abdelrahman-Amen/Car_Plate_Detection_using_YOLOv8

Abdelrahman-Amen/Centroid-in-Pattern_Recognition

This repository implements centroid-based pattern recognition, extracting features from images using grid cell centroids for classification in computer vision and image processing.

Abdelrahman-Amen/Chain-code-in-patter-recognition

Abdelrahman-Amen/Cifar10_Using_Convolutional_Neural_Network

Abdelrahman-Amen/Dynamic_Neural_Network

Abdelrahman-Amen/Fuzzy-C-Means-Clustering-from-scratch

Fuzzy C-Means (FCM) is a clustering algorithm that assigns membership degrees to data points, allowing for soft assignment to clusters. It offers flexibility, robustness to noise, interpretability, scalability, and versatility in various domains such as pattern recognition and data mining.

Abdelrahman-Amen/Housing-Price

Predicting housing prices with machine learning regression models. This project implements Linear Regression, Random Forest, and Decision Tree models for accurate predictions.

Abdelrahman-Amen/Fast_Text_NLP

FastText is a word embedding model by Facebook that captures word meanings, even for rare words, by using subword information, improving over traditional methods like word2vec.

Abdelrahman-Amen/Heart_Diseases_with_deployment

This project focuses on predicting heart disease using a comprehensive dataset containing patient information. The goal is to build machine learning models that can predict the presence of heart disease based on various health parameters.

Abdelrahman-Amen/hexapod

Hexapod Robot

Abdelrahman-Amen/Inception-Network-From-Scratch-and-Built_in

Explore the Inception Network, a powerful deep learning architecture designed for image classification. Uncover the efficiency of 1x1 convolutions, strategically used to reduce computational costs and capture intricate features at different scales, revolutionizing the way neural networks process information.

Abdelrahman-Amen/k-nearest-neighbors-KNN-from-scratch-and-Built_in

KNN is a basic machine learning algorithm used for classification and regression tasks. It predicts the class of a new data point based on the majority class of its nearest neighbors. KNN is simple, non-parametric, and learns directly from the training data without explicit training.

Abdelrahman-Amen/Kmeans_using_Centroid_and_Chain_Code_in_Pattern_Recognition

Abdelrahman-Amen/LenNet-5

LeNet-5 Image Classification project demonstrates the power of the LeNet convolutional neural network for character and digit recognition in grayscale images.

Abdelrahman-Amen/Logistic_Regression_From_Scratch

Logistic regression is a statistical technique primarily used for binary classification tasks. It predicts the probability of a binary outcome based on one or more predictor variables. Unlike linear regression, which predicts continuous outcomes, logistic regression deals with categorical outcomes.

Abdelrahman-Amen/Naive-Bayes-from-Scratch

Abdelrahman-Amen/Optimizers

Abdelrahman-Amen/Pattern_Recognition_System

Pattern recognition involves classifying data into categories based on features, playing a vital role in applications like image and speech recognition. This project implements a system that enhances classification accuracy by utilizing Grey Wolf Optimization for feature selection and a Gaussian Naive Bayes classifier for efficient classification.

Abdelrahman-Amen/Regression

Abdelrahman-Amen/Resnet50-From_Scratch_and_Built_in

ResNet-50, with 50 layers, excels in image classification by addressing the vanishing gradient problem. Skip connections facilitate seamless information flow, empowering the model for intricate feature learning. Its unique architecture makes ResNet-50 a robust choice for complex pattern recognition.

Abdelrahman-Amen/Second_Try

Abdelrahman-Amen/TD_IDF-from-scratch-and-built_in

Abdelrahman-Amen/Text_Generation_NLP_RNN_Arabic_and_English

Abdelrahman-Amen/Titanic-survival-prediction

The Titanic dataset includes passenger information such as survival status, ticket class, gender, age, family relations aboard, fare, cabin, and port of embarkation. It's widely used for predictive modeling to understand survival patterns based on passenger attributes.

Abdelrahman-Amen/Unsplash_Image_Search_Application

This project is a web-based application that allows users to search for images from Unsplash by entering a prompt. It retrieves and displays relevant, high-quality images from Unsplash, providing a simple and user-friendly interface for browsing photos.

Abdelrahman-Amen/VGG16-From-Scratch-and-Built_in

This project implements the powerful VGG-16 convolutional neural network for image classification, showcasing its efficiency with 3x3 filters, same padding, stride of 1, and 2x2 max-pooling for superior pattern recognition in diverse images.