NM-SRN v2.0 AGI Level 1 running on ESP32 - 3rd May 2025
Abstract This paper presents a significant breakthrough: the successful execution of the Neural-Matrix Synaptic Resonance Network (NM-SRN) v2.0, demonstrating AGI Level 1 capabilities, on an ESP32 microcontroller platform via the Wokwi simulator. This achievement highlights the potential of NM-SRN as a transparent, explainable, and inherently 'Safer by Design' Artificial General Intelligence architecture. We provide visual evidence from the simulation, showcasing core NM-SRN functionalities operating within the constraints of edge hardware, including resonance-based propagation and Fast Forward Learning (FFL) enabled by default through its Turing complete design. This work, part of the open-source 'ThinkSpace' PROJECT, validates the practical viability of running advanced, adaptable AI models in accessible, real-world environments. Source code is omitted due to intellectual property considerations.
Institutions
- Biokine (Israel) (IL)
- Neural Signals (United States) (US)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2025-05-04
- DOI
- https://doi.org/10.5281/zenodo.15335990
- Primary Topic
- Advanced Memory and Neural Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00