MicroMLP

The library is implemented in a single `microMLP.py` file, making integration and deployment on resource-constrained microcontrollers straightforward without complex dependencies.

Supports six activation functions including Heaviside, Sigmoid, TanH, and ReLU per layer, providing flexibility for different neural network designs as shown in the README tables.

Includes supervised learning with example management and Q-learning for reinforcement learning, specifically optimized for edge AI on devices like ESP32 and Pycom modules.

Enables saving and loading entire neural network structures to/from JSON files, facilitating portability and offline use, as demonstrated in the XOR example code.