A Swarm Optimization Solver Based on Ferroelectric Spiking Neural Networks
A Swarm Optimization Solver Based on Ferroelectric Spiking Neural Networks
复制标题
DOI：
10.3389/fnins.2019.00855
复制
发表时间：
2019-08
影响因子：
4.3
通讯作者：
Yan Fang;Z. Wang;Jorge Gomez;S. Datta;A. Khan;A. Raychowdhury
中科院分区：
文献类型：
--
作者：
Yan Fang;Z. Wang;Jorge Gomez;S. Datta;A. Khan;A. Raychowdhury
作为受生物神经系统启发的计算模型，尖峰神经网络（SNN）在人工智能领域继续显示出巨大的潜力，特别是在识别，推理和学习等任务中。虽然SNN专注于实现个体生物的高水平智能，但群智能（SI）是另一种生物启发模型，它模仿生物群的集体智能，即，鸟群、鱼群和蚁群。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有效和实用的解决方案。将人工智能的这两个不同的子领域连接起来，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，我们探讨了通过在SNN上实现广义SI模型来连接这两个模型的可行性。在所提出的计算范式中，我们使用SNN来代表群体中的代理，并使用尖峰发射率和尖峰定时对问题解决方案进行编码。耦合的神经元通过事件驱动的尖峰信号相互交流和调节动作电位，并使它们的动力学围绕最优解的状态同步。我们证明，这样的SI-SNN模型是能够有效地解决优化问题，如参数优化的连续函数和一个无处不在的组合优化问题，即旅行商问题与接近最优的解决方案。此外，我们证明了一个有效的实现这种神经动力学的新兴硬件平台上，即铁电场效应晶体管（FeFET）为基础的尖峰神经元。这种新兴的计算机模拟神经元由具有兴奋性和抑制性输入的紧凑的1 T-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高性能和高能效的优化求解器。
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 in-silico 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.