{"id":23550394,"url":"https://github.com/bushra-butt-17/deeplearning-projects","last_synced_at":"2025-07-22T11:33:30.973Z","repository":{"id":269409887,"uuid":"907324687","full_name":"Bushra-Butt-17/DeepLearning-Projects","owner":"Bushra-Butt-17","description":"This repository contains my assignments and projects related to deep learning, including implementations of fundamental concepts such as Linear Regression, Gradient Descent, Multi-Layer Perceptron (MLP), and more. Each section includes code, explanations, and relevant documentation. The goal of this repository is to showcase my learning journey.","archived":false,"fork":false,"pushed_at":"2024-12-23T14:32:56.000Z","size":11003,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-15T14:47:51.520Z","etag":null,"topics":["ames-housing-dataset","cat-notcat-classification","data-science","deep-learning","deep-neural-networks","exploratory-data-analysis","gradient-descent","iris-classification","learning-python","linear-regression","logistic-regression","mlp","mlp-classifier","visualization"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"unlicense","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Bushra-Butt-17.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-12-23T10:29:07.000Z","updated_at":"2024-12-31T10:58:43.000Z","dependencies_parsed_at":"2024-12-23T11:32:34.537Z","dependency_job_id":"a3d6ef57-9bf7-4c10-84a5-154937fad0e9","html_url":"https://github.com/Bushra-Butt-17/DeepLearning-Projects","commit_stats":null,"previous_names":["bushra-butt-17/deeplearning-projects"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Bushra-Butt-17/DeepLearning-Projects","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bushra-Butt-17%2FDeepLearning-Projects","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bushra-Butt-17%2FDeepLearning-Projects/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bushra-Butt-17%2FDeepLearning-Projects/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bushra-Butt-17%2FDeepLearning-Projects/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Bushra-Butt-17","download_url":"https://codeload.github.com/Bushra-Butt-17/DeepLearning-Projects/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bushra-Butt-17%2FDeepLearning-Projects/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265252495,"owners_count":23735081,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ames-housing-dataset","cat-notcat-classification","data-science","deep-learning","deep-neural-networks","exploratory-data-analysis","gradient-descent","iris-classification","learning-python","linear-regression","logistic-regression","mlp","mlp-classifier","visualization"],"created_at":"2024-12-26T10:16:05.596Z","updated_at":"2025-07-14T06:33:07.742Z","avatar_url":"https://github.com/Bushra-Butt-17.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🌟 Ultimate Deep Learning Projects: From Basics to Brilliance 🧠\n\n![image](https://github.com/user-attachments/assets/60ef079f-335b-4df7-85bf-ce7d848b7d8c)\n\n\n\n---\n\n# Iris Classification 🌸\n\nThis project demonstrates a deep learning model for classifying the **Iris** dataset, which contains three species of Iris flowers: Setosa, Versicolor, and Virginica. The dataset includes features such as sepal length, sepal width, petal length, and petal width for each species.\n\n## Key Steps 🔑:\n\n- **Data Preprocessing** 🧹: Clean the dataset and apply feature scaling to improve model performance.\n- **Model Architecture** 🏗️: Build a neural network using Keras for multi-class classification.\n- **Training \u0026 Evaluation** 📊: Train the model and evaluate its accuracy in classifying the Iris species.\n\n## Key Insights 🔍:\n\n- **Setosa's Distinct Sepal Length** 📏: Setosa typically has shorter sepal lengths, which are clearly visible in the **distribution plot**.  \n\n- **Overlap Between Versicolor and Virginica** 🤝: These two species show some overlap in sepal length, but Virginica generally has longer sepals.  \n\n- **Petal Length Distribution** 🌺: Setosa has a narrow range of petal lengths, while Versicolor and Virginica have broader distributions. Virginica generally has longer petals.  \n\n- **Pairplot Overview** 🔠: The **pairplot** shows that Setosa is easily distinguishable from Versicolor and Virginica, especially in terms of petal length and width, while Versicolor and Virginica overlap slightly.  \n\n👉 **[Explore the Full Project](https://github.com/Bushra-Butt-17/DeepLearning-Projects/tree/main/Iris-Data-Insights)**  \n\n---\n\n# 🏡 Ames Housing Price Prediction: Linear Regression with Gradient Descent\n\nThis project demonstrates how to build a linear regression model from scratch using the **Ames Housing Dataset** 🏘️. It includes:  \n\n- Implementing the **Gradient Descent algorithm** for optimizing model parameters.  \n- Analyzing the data to gain insights and visualize trends.  \n- Evaluating the model's performance using metrics like RMSE.  \n- Visualizing results such as **learning curves** and feature impacts.  \n\nThe project is organized as follows:  \n\n- **Main Notebook**: All analysis and code are consolidated in the `linear-regression-with-gd.ipynb` file.  \n- **Dataset**: Located in the `data` directory as `Ames_Housing.csv`.  \n- **Visualizations**: Plots and images are stored in the `visualizations` directory, showcasing learning curves and insights.  \n\n👉 **[Explore the Full Project](https://github.com/Bushra-Butt-17/DeepLearning-Projects/tree/main/Linear-Regression-with-GD)**  \n\nFeel free to check out the directory structure, dive into the notebook, and explore how linear regression works with Gradient Descent! 🚀\n\n---\n# 🐾 Logistic Regression with Neural Network: Cat Classifier  \n\n## 🚀 Overview  \nClassify 🐱 vs. 🐾 (non-cats) using **Logistic Regression** implemented from scratch. Understand core concepts like **forward propagation**, **backpropagation**, and **optimization**.  \n\n## 🗂️ Structure  \n- **`datasets/`**: Training \u0026 testing images.  \n- **`Logistic_Regression_with_Neural_Network.ipynb`**: Main notebook.  \n\n## 🔧 Requirements  \n- `numpy`, `matplotlib`, `PIL`, `scikit-learn`  \n\n## 🧠 Steps  \n1. **Data Preprocessing**: Flatten \u0026 normalize images.  \n2. **Training**: Update weights using gradient descent.  \n3. **Evaluation**: Analyze accuracy \u0026 confusion matrix.  \n\n## 📊 Results  \nEvaluate performance with metrics like accuracy and visualize results.  \n\n## 🎯 Conclusion  \nBuild a simple yet effective neural network to classify cats while learning foundational ML concepts!\n\n👉 **[Explore the Full Project](https://github.com/Bushra-Butt-17/DeepLearning-Projects/tree/main/Logistic%20Regression)**  \n\n---\n\n# 🚀 **MLP Planar Data Classification**\n\n---\n\nThis project demonstrates the power of **Multi-Layer Perceptron (MLP)** in classifying **planar data**, showcasing how neural networks can solve problems involving non-linearly separable datasets. With the help of **gradient descent optimization**, the MLP learns to create complex decision boundaries to classify the data points effectively.\n\n- **Key Features** ✨:\n  - **Planar Data Classification** using MLP 🤖: A hands-on approach to solving non-linearly separable classification tasks.\n  - **Gradient Descent Optimization** 🔄: The model learns by minimizing the binary cross-entropy loss function.\n  - **Intuitive Visualizations** 📊: Visualize the training process with plots like the decision boundary, loss curve, and accuracy progression, stored in the `Visualizations/` directory.\n  - **Step-by-Step Implementation** 📝: Detailed notebook with clear code comments for an educational understanding of MLP training.\n\n- **Technical Insights** ⚙️:\n  - **Activation Function**: Sigmoid 🟢\n  - **Loss Function**: Binary Cross-Entropy 📉\n  - **Optimizer**: Gradient Descent 🚴‍♂️\n  - **Metrics**: Accuracy 📈 and visualized decision boundaries for model evaluation.\n\n- **Directory Structure** 📂:\n  - **Main Notebook**: `MLP-Planar-Data-Classification.ipynb` 📝, where all the implementation takes place.\n  - **Visualizations Directory**: Contains key plots to track model performance, such as:\n    - **Decision Boundary** 🔵🟠\n    - **Loss Curve** 📉\n    - **Accuracy Progression** 📈\n\n- **Contributing** 🤝: Contributions are encouraged! Fork the repo, submit issues, or create pull requests for improvements and enhancements.\n\n- **Contact** 📧: For any questions or feedback, feel free to reach out!\n\n👉 **[Explore the Full Project](https://github.com/Bushra-Butt-17/DeepLearning-Projects/tree/main/Multiple%20Layer%20Perceptron)**  \n\n\n--- \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbushra-butt-17%2Fdeeplearning-projects","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbushra-butt-17%2Fdeeplearning-projects","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbushra-butt-17%2Fdeeplearning-projects/lists"}