Skatchkovsky Nicolas, Jang Hyeryung, Simeone Osvaldo
King's Communication, Learning and Information Processing (KCLIP) Lab, Department of Engineering, King's College London, London, United Kingdom.
Department of Artificial Intelligence, Dongguk University, Seoul, South Korea.
Front Comput Neurosci. 2022 Nov 16;16:1037976. doi: 10.3389/fncom.2022.1037976. eCollection 2022.
Among the main features of biological intelligence are energy efficiency, capacity for continual adaptation, and risk management uncertainty quantification. Neuromorphic engineering has been thus far mostly driven by the goal of implementing energy-efficient machines that take inspiration from the time-based computing paradigm of biological brains. In this paper, we take steps toward the design of neuromorphic systems that are capable of adaptation to changing learning tasks, while producing well-calibrated uncertainty quantification estimates. To this end, we derive online learning rules for spiking neural networks (SNNs) within a Bayesian continual learning framework. In it, each synaptic weight is represented by parameters that quantify the current epistemic uncertainty resulting from prior knowledge and observed data. The proposed online rules update the distribution parameters in a streaming fashion as data are observed. We instantiate the proposed approach for both real-valued and binary synaptic weights. Experimental results using Intel's Lava platform show the merits of Bayesian over frequentist learning in terms of capacity for adaptation and uncertainty quantification.
生物智能的主要特征包括能源效率、持续适应能力以及风险管理不确定性量化。到目前为止，神经形态工程主要受实现节能机器这一目标的驱动，这些机器借鉴了生物大脑基于时间的计算范式。在本文中，我们朝着设计能够适应不断变化的学习任务的神经形态系统迈出了步伐，同时产生校准良好的不确定性量化估计。为此，我们在贝叶斯持续学习框架内推导了脉冲神经网络（SNN）的在线学习规则。在该框架中，每个突触权重由量化先前知识和观测数据产生的当前认知不确定性的参数表示。所提出的在线规则在观测数据时以流方式更新分布参数。我们针对实值和二元突触权重实例化了所提出的方法。使用英特尔的Lava平台进行的实验结果表明，在适应能力和不确定性量化方面，贝叶斯学习优于频率主义学习。
