ON-OFF Neuromorphic ISING Machines using Fowler-Nordheim Annealers

2024-06-07

arXiv.org

AI Summary

Neuromorphic hardware struggles to asymptotically converge to the Ising ground state at low temperatures and requires graph-structure-dependent hyperparameter tuning. To address this, we propose NeuroSA—a brain-inspired architecture featuring an adaptive-threshold annealing mechanism grounded in Fowler–Nordheim quantum tunneling. This mechanism maps simulated annealing dynamics onto asynchronous ON-OFF spiking neurons, enabling hardware-level emulation of optimal low-temperature escape behavior and asymptotic convergence—without graph-specific hyperparameter adjustments. Evaluated on MAX-CUT and Maximum Independent Set benchmarks, NeuroSA achieves solution qualities concentrated within 99% of state-of-the-art (SOTA) results, with several instances surpassing current best-known solutions. Hardware validation on the SpiNNaker2 neuromorphic platform confirms its feasibility and efficacy.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Hardware-aware ML
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

We introduce NeuroSA, a neuromorphic architecture specifically designed to ensure asymptotic convergence to the ground state of an Ising problem using a Fowler-Nordheim quantum mechanical tunneling based threshold-annealing process. The core component of NeuroSA consists of a pair of asynchronous ON-OFF neurons, which effectively map classical simulated annealing dynamics onto a network of integrate-and-fire neurons. The threshold of each ON-OFF neuron pair is adaptively adjusted by an FN annealer and the resulting spiking dynamics replicates the optimal escape mechanism and convergence of SA, particularly at low-temperatures. To validate the effectiveness of our neuromorphic Ising machine, we systematically solved benchmark combinatorial optimization problems such as MAX-CUT and Max Independent Set. Across multiple runs, NeuroSA consistently generates distribution of solutions that are concentrated around the state-of-the-art results (within 99%) or surpass the current state-of-the-art solutions for Max Independent Set benchmarks. Furthermore, NeuroSA is able to achieve these superior distributions without any graph-specific hyperparameter tuning. For practical illustration, we present results from an implementation of NeuroSA on the SpiNNaker2 platform, highlighting the feasibility of mapping our proposed architecture onto a standard neuromorphic accelerator platform.

Problem

• Ensures asymptotic convergence to Ising problem ground state
• Solves combinatorial optimization problems like MAX-CUT
• Achieves state-of-the-art results without hyperparameter tuning

Innovation

• Neuromorphic architecture for Ising problem convergence
• Fowler-Nordheim tunneling-based threshold-annealing process
• Asynchronous ON-OFF neurons replicate simulated annealing dynamics