Authors:
Aashna Desai, Rugved Gramopadhye, Jashkumar Shah, Debabrata Das, R. Regin
Addresses:
Department of Information Technology, Pace University, New York, United States of America. Department of Information Technology, The University of Texas at Dallas, Texas, United States of America. Department of Information Technology, Illinois Institute of Technology, Chicago, Illinois, United States of America. Department of Information Technology, The University of Texas at Austin, Texas, United States of America. Department of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India.
Abstract:
Computer paradigms of decision-making from the past are strong but generally fall short of nature's adaptability of expression and energy efficiency in biological nervous systems. Here, the first breakthrough is achieved with a new hybrid computational paradigm that integrates living cerebral organoids directly into adaptive microcircuits to augment AI decision-making capabilities. Researchers present OI as an operational subunit of a computer entity, analogous to biological neural plasticity and advanced signalling mechanisms within an evolving cortical organoid. The experimental approach was to culture human stem cell-derived cerebral organoids on high-density multi-electrode arrays (MEAs) and to stimulate them with sophisticated decision-making task scenarios constructed from a newly synthesized dataset, SORN-1. The neural activity output was processed, regulated, and used as a dynamic input stream to enhance a deep reinforcement learning agent. The main software tools used in this research study were the Python programming language, complemented by the TensorFlow and Scikit-learn libraries for computational modelling, and a proprietary NPI-3 for real-time data recording and stimulation control. Our findings affirm the OI-augmented model's revolutionary leap in learning rate, novel stimulus adaptation, and decision-making across all domains compared to its silicon counterparts, preparing the next generation of bio-hybrid computing.
Keywords: Organoid Intelligence (OI); Brain-Inspired Computing; Simulated Organoid-Response Nexus (SORN-1); Bio-Hybrid-AI; Artificial Intelligence (AI); Tensorflow and Scikit-Learn; Energy Efficiency; Neuro-Pulse Interface (NPI-3).
Received: 24/09/2024, Revised: 09/11/2024, Accepted: 19/01/2025, Published: 07/12/2025
DOI: 10.64091/ATICL.2025.000231
AVE Trends in Intelligent Computer Letters, 2025 Vol. 1 No. 4 , Pages: 170-178