Spike-timing-dependent plasticity learning of coincidence detection with passively integrated memristive circuits

Abstract

Spiking neural networks, the most realistic artificial representation of biological nervous systems, are promising due to their inherent local training rules that enable low-overhead online learning, and energy-efficient information encoding. Their downside is more demanding functionality of the artificial synapses, notably including spike-timing-dependent plasticity, which makes their compact efficient hardware implementation challenging with conventional device technologies. Recent work showed that memristors are excellent candidates for artificial synapses, although reports of even simple neuromorphic systems are still very rare. In this study, we experimentally demonstrate coincidence detection using a spiking neural network, implemented with passively integrated metal-oxide memristive synapses connected to an analogue leaky-integrate-and-fire silicon neuron. By employing spike-timing-dependent plasticity learning, the network is able to robustly detect the coincidence by selectively increasing the synaptic efficacies corresponding to the synchronized inputs. Not surprisingly, our results indicate that device-to-device variation is the main challenge towards realization of more complex spiking networks.

Spike‐Timing‐Dependent and Spike‐Shape‐Independent Plasticities with Dopamine‐Like Modulation in Nanocomposite Memristive Synapses

“…On the contrary, in spiking NS, it is possible to realize at least partially unsupervised learning, e.g., in terms of a spike-timing-dependent plasticity (STDP) mechanism. [30][31][32][33][34][35] Basic STDP is a local learning rule expressing a causal relationship between neurons. [36] STDP was shown to emerge naturally in different memristive devices.…”

Memristive and CMOS Devices for Neuromorphic Computing

“…Moreover, note that this scheme offers the opportunity to finely tune the shape of STDP characteristics, by suitably designing the PRE spike waveform [144]. Taking inspiration from this approach based on overlapping spikes across the memristive device, more recently, other significant STDP demonstrations were achieved in individual two-terminal memristive devices, thus enabling unsupervised learning in small-scale memristive SNNs [145][146][147][148][149]. However, the synapse implementation using individual two-terminal memristive devices might suffer from serious issues, such as (i) the requirement to control the current during set transition in RRAM devices to avoid an uncontrollable CF growth [64], which would reduce the synapse reliability during potentiation; (ii) the sneak paths challenging the operation of crossbar arrays; and (iii) the high energy consumption.…”

Modeling and Simulation of Spiking Neural Networks with Resistive Switching Synapses

“…This process, which is referred to as unsupervised learning, relies on schemes such as STDP and SRDP that adjust synaptic weights of neural networks according to timing or rate of spikes encoding information such as images and sounds. In particular, unsupervised learning of visual patterns has recently attracted increasing interest leading to many simulation/hardware demonstrations of SNNs with RRAM synapses capable of STDP [18,23,24,[26][27][28][29][30] and SRDP [25,31]. Figure 4.5a illustrates a SNN inspired to perceptron network model developed by Rosenblatt in the late 1950s [32] consisting of 64 PREs fully connected to a single POST.…”