A coupled spintronic-oscillator array has been considered attractive for neuromorphic computing applications. Experimental reports have shown the nanoconstriction geometry to be a relatively easier-to-fabricate platform for implementing such spin oscillators, but most prior reports on training and inference algorithms for neuromorphic computing using spin oscillators have been mostly restricted to the nanopillar geometry. Also, those prior reports involve updating the natural frequency values of the oscillators and moving the synchronization regions onto the data clusters during the offline learning phase, which has associated challenges. In this context, we design and simulate a novel artificial neural network (ANN)—oscillator neural network (ONN)—algorithm wherein, in the offline learning phase, the weight parameters of the ANN are updated such that the data clusters are instead moved to the synchronization regions of spin Hall nanooscillators (SHNOs) in the nanoconstriction geometry, as obtained through micromagnetic simulations. We further simulate the on-chip inference part of the ANN-ONN algorithm, where the ANN is implemented on a crossbar array of domain-wall synapse devices, as simulated here through micromagnetics, and the ONN is implemented on nanoconstriction SHNOs. We show successful data classification for both binary and multiclass classification tasks to demonstrate the generalizability of our proposed scheme.

Close

PrevNext

View figure in article

• Domain walls
• Neuromorphic computing
• Spintronics
• Synapses
• Artificial neural networks
• Nano-oscillators
• Nanotechnology
• Machine learning