The development of the Breast Cancer Detection Model involved a meticulous approach to machine learning. I manually implemented the neural network, carefully constructing both backward and forward propagation algorithms. To enhance the model's performance, I incorporated various optimization techniques, such as gradient descent with momentum and RMSprop, which helped to speed up the learning process and improve accuracy. The model was trained and tested using CSV data from a breast cancer dataset, ensuring a comprehensive evaluation of its predictive capabilities. Through rigorous testing, I achieved a remarkable test set accuracy of 99.98%, demonstrating the model's effectiveness in detecting breast cancer.
- Python: For implementing the machine learning algorithms and data analysis.
- Numpy: To handle numerical computations and facilitate the implementation of optimization techniques.
- Pandas: For data manipulation and management, enabling efficient handling of the CSV dataset.
- CSV Data: Provided a comprehensive set of features for training and testing the model, ensuring robust evaluation.
To view the results of the model, clone the repository, then running the notebook inside the "nn.ipynb".