Added cuda support for my custom neural architecture

The architecture is designed to simulate a neural network with hierarchical memory management, dynamic adaptation, and performance optimization. The goal of this architecture is to present an alternative to modern neural models, which are often complex and resource-intensive, taking inspiration from our brains, neurons are decentralized organized in layers, allowing them to interact with themselves and change theirselves overtime in more than just sates and weights, while also creating a dynamic memory system.
https://github.com/Okerew/Neural-Web/tree/main
also fixed some things in the cpu versions