On the next generation for neuromorphic computing and neuromorphic AI

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Not applicable — no quantitative effect size reported

• Primary Outcome: Conceptual identification of dynamical behaviours in cortex-like neural column sub-networks that are absent from current neuromorphic chip designs, and proposal of a mathematical framework to encompass both human cognitive processing and future neuromorphic architectures

• Nnt Or Sensitivity: Not applicable — theoretical review; no diagnostic, therapeutic, or prognostic metrics calculated

• Confidence Interval: Not reported

Clinical Application

The proposed neuromorphic architectures and mathematical frameworks are at a pre-prototype conceptual stage. Clinical translation is speculative and likely many years distant. No implementation pathway, regulatory strategy, or clinical validation plan is described No direct relevance to current PBS listings or TGA-approved devices. The Australian Digital Health Agency and RACGP are increasingly engaged with AI governance in clinical settings, and the paper's observations about cognitive biases inherent in neuromorphic AI systems are pertinent to Australian frameworks for AI safety in healthcare (e.g., the Australian Government's Voluntary AI Safety Standard 2024 and the TGA's emerging guidance on AI-enabled medical devices). Clinicians and health informaticians involved in AI procurement and governance should note the paper's argument that neuromorphic AI may inherit human-like systematic errors and blind spots — a consideration for clinical risk management that aligns with RACGP's position on AI in general practice. Not directly applicable to any clinical patient population at present. Indirectly relevant to healthcare informaticians, clinical AI developers, and health system architects considering next-generation AI-assisted clinical decision support, medical imaging analysis, or safety-critical clinical AI deployment

Abstract

As we learn more about the inner cognitive workings of the brain's information processing and decision-making behaviours, this naturally leads us to consider alternative and additional ways to process information, from chips and architectures through the generation of insights and decisions. In turn, this suggests some options that might respond to challenges that are not addressable by the present state-of-the-art. By their nature, however, they may develop some common features and idiosyncrasies that are associated with human cognition, such as individual expertise and blind spots, illusions, systematic errors and transient mindsets, as well as evolutionarily advantageous fast-thinking facilities, which are applicable within novel and data-poor circumstances. We discuss some of the lessons learned from the reverse engineering of very large-scale neuron-to-neuron simulations (1B neurons) within cortex-like, network-of-networks, architectures. We identify some elements of the dynamical behaviour of the inner sub-networks (neural columns) that are not exhibited by present-day neuromorphic chips, owing to conceptual and design limitations. We describe a novel mathematical framework that might encompass human cognitive processing alongside various future neuromorphic processing concepts. We also identify certain elements of human cognition, reasoning and performance that present-day chips and present-day artificial intelligence (AI) simply cannot fully emulate (match to a high standard, in some artificial way), or simulate (achieve in the same way). We discuss how these aspects might catalyse some new fields of development for both processors and AI methodologies. In short, we discuss how future research and development will respond in radical ways that are precluded by most present-day technologies. This article is part of the theme issue 'Safe, secure and robust AI for safety-critical systems'.

References

1. 1.Grindrod, P. (2026). On the next generation for neuromorphic computing and neuromorphic AI. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences. https://doi.org/10.1098/rsta.2025.0122