Spiking neural network

Electrical engineering

Physics

Neuromorphic engineering

Mathematics

Engineering physics

Phase-change memory

Distributed computing

Statistics

Computer architecture

Memristor

Engineering

Phase change

Artificial intelligence

Unconventional computing

Electronic engineering

Efficient energy use

Computer science

Realization (probability)

Artificial neural network

Nature Communications

Neuromorphic computing has emerged as a promising avenue towards building the next generation of intelligent computing systems. It has been proposed that memristive devices, which exhibit history-dependent conductivity modulation, could efficiently represent the synaptic weights in artificial neural networks. However, precise modulation of the device conductance over a wide dynamic range, necessary to maintain high network accuracy, is proving to be challenging. To address this, we present a multi-memristive synaptic architecture with an efficient global counter-based arbitration scheme. We focus on phase change memory devices, develop a comprehensive model and demonstrate via simulations the effectiveness of the concept for both spiking and non-spiking neural networks. Moreover, we present experimental results involving over a million phase change memory devices for unsupervised learning of temporal correlations using a spiking neural network. The work presents a significant step towards the realization of large-scale and energy-efficient neuromorphic computing systems.

Neuromorphic computing with multi-memristive synapses