Fang Yan, Wang Zheng, Gomez Jorge, Datta Suman, Khan Asif I, Raychowdhury Arijit
School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, United States.
Department of Electrical Engineering, University of Notre Dame, Notre Dame, IN, United States.
Front Neurosci. 2019 Aug 13;13:855. doi: 10.3389/fnins.2019.00855. eCollection 2019.
As computational models inspired by the biological neural system, spiking neural networks (SNN) continue to demonstrate great potential in the landscape of artificial intelligence, particularly in tasks such as recognition, inference, and learning. While SNN focuses on achieving high-level intelligence of individual creatures, Swarm Intelligence (SI) is another type of bio-inspired models that mimic the collective intelligence of biological swarms, i.e., bird flocks, fish school and ant colonies. SI algorithms provide efficient and practical solutions to many difficult optimization problems through multi-agent metaheuristic search. Bridging these two distinct subfields of artificial intelligence has the potential to harness collective behavior and learning ability of biological systems. In this work, we explore the feasibility of connecting these two models by implementing a generalized SI model on SNN. In the proposed computing paradigm, we use SNNs to represent agents in the swarm and encode problem solutions with the spike firing rate and with spike timing. The coupled neurons communicate and modulate each other's action potentials through event-driven spikes and synchronize their dynamics around the states of optimal solutions. We demonstrate that such an SI-SNN model is capable of efficiently solving optimization problems, such as parameter optimization of continuous functions and a ubiquitous combinatorial optimization problem, namely, the traveling salesman problem with near-optimal solutions. Furthermore, we demonstrate an efficient implementation of such neural dynamics on an emerging hardware platform, namely ferroelectric field-effect transistor (FeFET) based spiking neurons. Such an emerging neuron is composed of a compact 1T-1FeFET structure with both excitatory and inhibitory inputs. We show that the designed neuromorphic system can serve as an optimization solver with high-performance and high energy-efficiency.
作为受生物神经系统启发的计算模型，脉冲神经网络（SNN）在人工智能领域持续展现出巨大潜力，尤其在识别、推理和学习等任务中。虽然SNN专注于实现个体生物的高级智能，但群体智能（SI）是另一类受生物启发的模型，它模仿生物群体（如鸟群、鱼群和蚁群）的集体智能。SI算法通过多智能体元启发式搜索为许多困难的优化问题提供了高效实用的解决方案。将人工智能的这两个不同子领域联系起来，有可能利用生物系统的集体行为和学习能力。在这项工作中，我们通过在SNN上实现一个广义的SI模型来探索连接这两种模型的可行性。在所提出的计算范式中，我们使用SNN来表示群体中的智能体，并通过脉冲发放率和脉冲时间对问题解决方案进行编码。耦合神经元通过事件驱动的脉冲相互通信并调制彼此的动作电位，并围绕最优解的状态同步它们的动态。我们证明，这样的SI - SNN模型能够有效地解决优化问题，如连续函数的参数优化以及一个普遍存在的组合优化问题，即具有近似最优解的旅行商问题。此外，我们展示了这种神经动力学在一个新兴硬件平台上的高效实现，即基于铁电场效应晶体管（FeFET）的脉冲神经元。这种新兴神经元由具有兴奋性和抑制性输入的紧凑1T - 1FeFET结构组成。我们表明，所设计的神经形态系统可以作为一个具有高性能和高能效的优化求解器。
