.png){kind=icon}
.png){kind=icon}
Return
A Memristor-Based Learning Engine for Synaptic Trace-Based Online Learning
.png){kind=icon}
OA
AI
DOI：10.1109/TBCAS.2023.3291021.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The memristor has been extensively used to facilitate the synaptic online learning of brain-inspired spiking neural networks (SNNs). However, the current memristor-based work can not support the widely used yet sophisticated trace-based learning rules, including the trace-based Spike-Timing-Dependent Plasticity (STDP) and the Bayesian Confidence Propagation Neural Network (BCPNN) learning rules. This paper proposes a learning engine to implement trace-based online learning, consisting of memristor-based blocks and analog computing blocks. The memristor is used to mimic the synaptic trace dynamics by exploiting the nonlinear physical property of the device. The analog computing blocks are used for the addition, multiplication, logarithmic and integral operations. By organizing these building blocks, a reconfigurable learning engine is architected and realized to simulate the STDP and BCPNN online learning rules, using memristors and 180 nm analog CMOS technology. The results show that the proposed learning engine can achieve energy consumption of 10.61 pJ and 51.49 pJ per synaptic update for the STDP and BCPNN learning rules, respectively, with a 147.03x and 93.61x reduction compared to the 180 nm ASIC counterparts, and also a 9.39x and 5.63x reduction compared to the 40 nm ASIC counterparts. Compared with the state-of-the-art work of Loihi and eBrainII, the learning engine can reduce the energy per synaptic update by 11.31x and 13.13x for trace-based STDP and BCPNN learning rules, respectively.
Keywords:
Memristors
Engines
Neuromorphics
Voltage
Synapses
Computational modeling
Biological neural networks
Bayesian confidence propagation neural network (BCPNN)
learning engine
memristor
online learning
spiking neural network (SNN)
spike-timing-dependent plasticity (STDP)
trace dynamics
Journal
IF:
5.2
Papers:
9.7K
Citations:
2.2W