Loading repository data…
Loading repository data…
MUGISHA-Pascal / repository
A variety of projects expressing my full journey in machine learning and deep learning using python and jupyter notebook for documentation
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
A comprehensive collection of machine learning projects, tutorials, experiments, and learning sessions covering various ML algorithms, datasets, and real-world applications.
.
├── notebooks/ # Jupyter notebooks organized by purpose
│ ├── tutorials/ # Learning materials and algorithm implementations
│ │ ├── algorithms/ # Linear regression, MNIST, and other algorithms
│ │ ├── backpropagation/
│ │ ├── computer-vision/
│ │ └── convolutional-neural-network/
│ ├── examples/ # Dataset examples and demonstrations
│ │ ├── breastCancer.ipynb
│ │ ├── CaliforniaHousing.ipynb
│ │ └── SVM(irisdataset).ipynb
│ ├── experiments/ # Test notebooks and custom implementations
│ │ ├── CSV_to_dataset_keras.ipynb
│ │ └── Keras_custom_model.ipynb
│ └── visualization/ # Data visualization notebooks and resources
│ └── data_visualization.ipynb
├── projects/ # Production-ready ML projects with Flask APIs
│ ├── breast-cancer-project/
│ ├── california-housing-project/
│ ├── diabetes-project/
│ ├── irisFeature-project/
│ ├── music-genre-generation-project/
│ ├── student-grade-project/
│ ├── student_performance_index/
│ ├── videoGame-project/
│ └── wine-project/
└── sessions/ # Learning sessions and practice work
├── 02-02-2026/
├── 19-01-2026/
└── 22-01-2026_Classification/
notebooks/tutorials/ for algorithm implementations and learning materialsnotebooks/examples/ for dataset-specific demonstrations (Breast Cancer, California Housing, Iris SVM)notebooks/experiments/ for custom Keras models and data processing techniquesprojects/ for complete ML applications with APIs and demossessions/ for dated learning sessions and classification workEach project folder typically contains:
train.py) - Model training and evaluationapp.py) - REST API for model predictionsmodel/) - Serialized model filesdemo/, nodeApp/) - Frontend interfaces for testingComprehensive learning materials covering:
Real-world dataset implementations:
Custom implementations and explorations:
Data analysis and visualization techniques for ML datasets
Dated learning sessions containing practice work, experiments, and specific topic explorations (e.g., classification techniques, recommendation systems)