Michele Laurelli

Michele Laurelli

As large-scale AI systems proliferate, ensuring compliance with data privacy laws such as the General Data Protection Regulation (GDPR) has become critical. This paper introduces Brain Surgery, a transformative methodology for making every local AI model GDPR-ready by enabling real-time privacy management and targeted unlearning. Building on advanced techniques such as Embedding-Corrupted Prompts (ECO Prompts), blockchain-based privacy management, and privacy-aware continual learning, Brain Surgery provides a modular solution that can be deployed across various AI architectures. This tool not only ensures compliance with privacy regulations but also empowers users to define their own privacy limits, creating a new paradigm in AI ethics and governance.

Michele Laurelli

This paper presents Adaptive Meta-Domain Transfer Learning (AMDTL), a novel methodology that combines principles of meta-learning with domain-specific adaptations to enhance the transferability of artificial intelligence models across diverse and unknown domains. AMDTL aims to address the main challenges of transfer learning, such as domain misalignment, negative transfer, and catastrophic forgetting, through a hybrid framework that emphasizes both generalization and contextual specialization. The framework integrates a meta-learner trained on a diverse distribution of tasks, adversarial training techniques for aligning domain feature distributions, and dynamic feature regulation mechanisms based on contextual domain embeddings. Experimental results on benchmark datasets demonstrate that AMDTL outperforms existing transfer learning methodologies in terms of accuracy, adaptation efficiency, and robustness. This research provides a solid theoretical and practical foundation for the application of AMDTL in various fields, opening new perspectives for the development of more adaptable and inclusive AI systems.

Michele Laurelli

Proton-boron (p-11B) fusion presents a promising path towards sustainable, neutron-free energy generation. However, its implementation is hindered by extreme operational conditions, such as plasma temperatures exceeding billions of degrees and the complexity of controlling high-energy particles. Traditional control systems face significant challenges in managing the highly dynamic and non-linear behavior of the plasma. In this paper, we propose a novel approach utilizing backpropagation-based neural networks to autonomously control key parameters in a proton-boron fusion reactor. Our method leverages real-time feedback and learning from physical data to adapt to changing plasma conditions, offering a potential breakthrough in stable and efficient p-11B fusion. Furthermore, we expand on the scalability and generalization of our approach to other fusion systems and future AI technologies.