develop

[jzsmoreno]

This pull request introduces significant performance optimizations to the engine, new functionality for calculating classification metrics, and an illustrative Jupyter Notebook example demonstrating the application of likelihood in deep learning models.

New Features

• Added functions for calculating common classification metrics, such as accuracy, precision, recall, and F1 score.
• Provided example usage of these metrics with popular deep learning libraries, including TensorFlow.

Documentation and Example Usage

• Updated documentation with instructions for using the new classification metric functions.
• Included a Jupyter Notebook example that demonstrates how to apply likelihood in deep learning models.

General Improvements

• Enhanced code organization and structure for improved maintainability.
• Improved error handling and logging for better debugging and traceability.

This pull request enhances the optimization engine’s performance, introduces new functionality for classification metrics, updates the documentation, and improves code quality and usability. The Jupyter Notebook example serves as a practical guide for leveraging likelihood in deep learning models.