IMAINET: An Immune Algorithm-Inspired Neural Network Framework

IMAINET is a self-organizing neural network framework inspired by immune algorithms such as clonal selection and affinity maturation. The architecture features a two-phase learning process: the first phase self-organizes hidden units based on immune principles, while the second phase learns the output mapping using various optimization strategies.

IMAINET is built with PyTorch for flexible gradient-based learning and supports metaheuristic algorithms via Mealpy, enabling robust optimization of network weights. Additionally, it offers an option for closed-form training using least squares estimation (e.g., ridge regression).

Wrapped in Scikit-Learn's BaseEstimator, IMAINET is easy to integrate into existing ML workflows, supporting pipelines, cross-validation, and hyperparameter tuning.