{"data":{"full_name":"mohamedkhayat/DIYNeuralNet","name":"DIYNeuralNet","description":"A lightweight deep learning framework implemented from scratch using NumPy/CuPy. supports customizable architectures, forward and back propagation, dropout, He/Glorot init, and mini-batch training. Designed for flexibility,it provides a foundation for building neural networks while giving insights into the inner workings of deep learning models","stars":6.0,"forks":0.0,"language":"Jupyter Notebook","license":"MIT","archived":0.0,"subcategory":"numpy-based-neural-networks","last_pushed_at":"2026-01-01T18:40:19+00:00","pypi_package":null,"npm_package":null,"downloads_monthly":0.0,"dependency_count":0.0,"commits_30d":null,"reverse_dep_count":0.0,"maintenance_score":6.0,"adoption_score":4.0,"maturity_score":16.0,"community_score":0.0,"quality_score":26.0,"quality_tier":"experimental","risk_flags":"['no_package', 'no_dependents']"},"meta":{"timestamp":"2026-04-08T11:14:57.268509+00:00"}}