Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Studies in systems, decision and control

Quantum-Enhanced Federated Learning Framework for Next-Generation AIoT Systems: Bridging Neuromorphic Computing and Environmental Intelligence

Viraj P. Tathavadekar, Nitin R. Mahankale

Published Oct 3, 2026• 0 citations
Publisher
DOI
10.1007/978-3-032-32770-3_18

Related papers

Quantum federated learning: architectural elements and future directions

Siva Sai, Abhishek Sawaika, Prabhjot Singh +1 more

arXiv:2510.17642•Elsevier eBooks•Jan 1, 2026•9 citations

Neuromorphic-Quantum Hybrid Learning: The Next Evolution Beyond Deep Learning

Soham Khadse

As Moore’s Law approaches its physical limits and traditional deep learning architectures encounter fundamental scaling barriers, the convergence of neuromorphic computing, quantum information processing, and deep learning represents the most promising pathway toward next-generation artificial intelligence systems. Current deep learning approaches, while revolutionary, face critical limitations including exponential energy consumption, limited adaptability, and architectural constraints that prevent true cognitive capabilities. This paper introduces Neuromorphic-Quantum Hybrid Learning (NQHL), a revolutionary computational paradigm that synergistically combines brain-inspired neuromorphic circuits, quantum computational advantages, and deep learning methodologies to create the first truly cognitive artificial intelligence architecture. Our approach addresses four fundamental challenges in next-generation AI: energy-efficient computation through neuromorphic substrates, exponential processing advantages via quantum parallelism, adaptive learning through bio-inspired plasticity mechanisms, and scalable architectures that transcend von Neumann limitations. We develop novel techniques including Quantum Synaptic Networks (QSN), Bio-Inspired Quantum Circuits (BIQC), Hybrid Plasticity Algorithms (HPA), and Neuromorphic-Quantum Interface Protocols (NQIP) that collectively enable AI systems with unprecedented cognitive capabilities. Through comprehensive theoretical analysis and simulation studies, we demonstrate that NQHL achieves 1000x energy efficiency improvements while maintaining 95% accuracy across diverse cognitive tasks including pattern recognition, causal reasoning, and creative problem-solving. Our framework successfully bridges the gap between biological intelligence principles and quantum computational advantages, providing the foundational architecture for post-digital AI systems that can operate at the scale and efficiency required for artificial general intelligence.

Journal of Pioneering Artificial Intelligence Research•Oct 1, 2025•0 citations

Agentic Hybrid Quantum–Neuromorphic AI Architecture With Explainable Reinforcement Learning for Next-Generation Intelligent Systems

Divyanshu Sinha, Udit Mamodiya, Indra Kishor +2 more

Artificial intelligence systems are shifting away to passive prediction systems into architectures that are supposed to rationalize and modify according to their needs as well as explain what they are doing. The current methods tend to maximize the precision at the expense of transparency and long-term flexibility, creating a gap in the systems with both accountable reasoning and learning processes. To solve this, we present an Agentic Hybrid Quantum -Neuromorphic AI system with an Explainable Reinforcement Learning core. It consists of a combination of quantum-assisted exploration, spiking neuromorphic adaptation, interpretable policy optimization to enable the system to adapt computational strategy depending on the dynamics of rewards, confidence, and environmental change. Experiments exhibit enhanced convergence speed, ability to maintain behavior in the case of sudden changes in the environment and a far greater enhancement in explanation coherence than traditional reinforcement learning agents and adaptive immersive systems.

Advances in computational intelligence and robotics book series•Mar 4, 2026•5 citations

Quantum Federated Learning: Progress, Challenges, and Opportunities

Sanchita Saha, Arup Kumar Chattopadhyay, Amitava Nag

Algorithms for intelligent systems•Jan 1, 2025•2 citations

Quantum-Enhanced Federated Learning: Pushing the Boundaries of Privacy and Speed in Distributed AI

Kirti, Charu Sood, Shubneet +3 more

Communications in computer and information science•Jan 1, 2026•0 citations

Toward Sustainable Edge Intelligence: Quantum-Inspired Spiking Neural Networks-Aided Federated Learning Approach

Quan Thanh Dao, Wei Yang Bryan Lim, B. D. E. McNiven +4 more

With the rapid expansion of edge devices, federated learning (FL) has emerged as a critical paradigm for enabling collaborative intelligence while preserving data privacy. However, deploying deep learning models on resource-constrained edge hardware remains challenging due to high computational and energy demands. To address this, we propose a novel quantum-inspired neuromorphic federated learning framework, called FL-quantum leaky integrate-and-fire (FL-QLIF). At the core of our approach is an enhanced QLIF neuron model that utilizes quantum rotation gates to simulate synaptic integration and membrane potential leakage simultaneously, offering a mathematically robust and computationally efficient alternative to traditional activation functions. We rigorously validate the framework through extensive experiments, demonstrating that its convergence behavior closely aligns with theoretical predictions regarding learning rates and local update steps. Extensive experiments on MNIST, KMNIST, and FashionMNIST datasets demonstrate that FL-QLIF achieves test accuracy comparable to classical artificial neural networks (ANNs) while significantly outperforming standard variational quantum neural networks (QNNs), particularly in statistically heterogeneous (non-iid) environments. Furthermore, our energy analysis reveals that the proposed framework delivers substantial efficiency gains, reducing energy consumption by$4.4\times$to$10\times$compared to ANN baselines. Finally, we validate the system's scalability, showing robust performance even under low client participation rates (10%), establishing FL-QLIF as a viable solution for sustainable, privacy-preserving edge intelligence.

IEEE Transactions on Network Science and Engineering•Jan 1, 2026•0 citations
As Moore’s Law approaches its physical limits and traditional deep learning architectures encounter fundamental scaling barriers, the convergence of neuromorphic computing, quantum information processing, and deep learning represents the most promising pathway toward next-generation artificial intelligence systems. Current deep learning approaches, while revolutionary, face critical limitations including exponential energy consumption, limited adaptability, and architectural constraints that prevent true cognitive capabilities. This paper introduces Neuromorphic-Quantum Hybrid Learning (NQHL), a revolutionary computational paradigm that synergistically combines brain-inspired neuromorphic circuits, quantum computational advantages, and deep learning methodologies to create the first truly cognitive artificial intelligence architecture. Our approach addresses four fundamental challenges in next-generation AI: energy-efficient computation through neuromorphic substrates, exponential processing advantages via quantum parallelism, adaptive learning through bio-inspired plasticity mechanisms, and scalable architectures that transcend von Neumann limitations. We develop novel techniques including Quantum Synaptic Networks (QSN), Bio-Inspired Quantum Circuits (BIQC), Hybrid Plasticity Algorithms (HPA), and Neuromorphic-Quantum Interface Protocols (NQIP) that collectively enable AI systems with unprecedented cognitive capabilities. Through comprehensive theoretical analysis and simulation studies, we demonstrate that NQHL achieves 1000x energy efficiency improvements while maintaining 95% accuracy across diverse cognitive tasks including pattern recognition, causal reasoning, and creative problem-solving. Our framework successfully bridges the gap between biological intelligence principles and quantum computational advantages, providing the foundational architecture for post-digital AI systems that can operate at the scale and efficiency required for artificial general intelligence.
Artificial intelligence systems are shifting away to passive prediction systems into architectures that are supposed to rationalize and modify according to their needs as well as explain what they are doing. The current methods tend to maximize the precision at the expense of transparency and long-term flexibility, creating a gap in the systems with both accountable reasoning and learning processes. To solve this, we present an Agentic Hybrid Quantum -Neuromorphic AI system with an Explainable Reinforcement Learning core. It consists of a combination of quantum-assisted exploration, spiking neuromorphic adaptation, interpretable policy optimization to enable the system to adapt computational strategy depending on the dynamics of rewards, confidence, and environmental change. Experiments exhibit enhanced convergence speed, ability to maintain behavior in the case of sudden changes in the environment and a far greater enhancement in explanation coherence than traditional reinforcement learning agents and adaptive immersive systems.
With the rapid expansion of edge devices, federated learning (FL) has emerged as a critical paradigm for enabling collaborative intelligence while preserving data privacy. However, deploying deep learning models on resource-constrained edge hardware remains challenging due to high computational and energy demands. To address this, we propose a novel quantum-inspired neuromorphic federated learning framework, called FL-quantum leaky integrate-and-fire (FL-QLIF). At the core of our approach is an enhanced QLIF neuron model that utilizes quantum rotation gates to simulate synaptic integration and membrane potential leakage simultaneously, offering a mathematically robust and computationally efficient alternative to traditional activation functions. We rigorously validate the framework through extensive experiments, demonstrating that its convergence behavior closely aligns with theoretical predictions regarding learning rates and local update steps. Extensive experiments on MNIST, KMNIST, and FashionMNIST datasets demonstrate that FL-QLIF achieves test accuracy comparable to classical artificial neural networks (ANNs) while significantly outperforming standard variational quantum neural networks (QNNs), particularly in statistically heterogeneous (non-iid) environments. Furthermore, our energy analysis reveals that the proposed framework delivers substantial efficiency gains, reducing energy consumption by4.4×4.4\times4.4×to10×10\times10×compared to ANN baselines. Finally, we validate the system's scalability, showing robust performance even under low client participation rates (10%), establishing FL-QLIF as a viable solution for sustainable, privacy-preserving edge intelligence.