Synchronous Unsupervised STDP Learning with Stochastic STT-MRAM Switching
This addresses fabrication and stochasticity issues in neuromorphic hardware for researchers, though it is incremental as it builds on prior asynchronous STT-MRAM methods.
The paper tackled the challenge of implementing analog-like synapse weights in neuromorphic systems by proposing a synchronous spiking neural network using stochastic STT-MRAM switching, achieving 90% inference accuracy on MNIST.
The use of analog resistance states for storing weights in neuromorphic systems is impeded by fabrication imprecision and device stochasticity that limit the precision of synapse weights. This challenge can be resolved by emulating analog behavior with the stochastic switching of the binary states of spin-transfer torque magnetoresistive random-access memory (STT-MRAM). However, previous approaches based on STT-MRAM operate in an asynchronous manner that is difficult to implement experimentally. This paper proposes a synchronous spiking neural network system with clocked circuits that perform unsupervised learning leveraging the stochastic switching of STT-MRAM. The proposed system enables a single-layer network to achieve 90% inference accuracy on the MNIST dataset.