Plasticity-Enhanced Domain-Wall MTJ Neural Networks for Energy-Efficient Online Learning
This work addresses energy efficiency in online learning systems for hardware implementation, though it appears incremental as it builds on existing DW-MTJ technology with neuroscience-inspired plasticity rules.
The researchers tackled the challenge of implementing energy-efficient online learning by developing a multi-stage neural network system using domain-wall magnetic tunnel junction (DW-MTJ) devices, achieving learning budgets below 20 μJ for large machine learning tasks while enabling quick generalization with few samples.
Machine learning implements backpropagation via abundant training samples. We demonstrate a multi-stage learning system realized by a promising non-volatile memory device, the domain-wall magnetic tunnel junction (DW-MTJ). The system consists of unsupervised (clustering) as well as supervised sub-systems, and generalizes quickly (with few samples). We demonstrate interactions between physical properties of this device and optimal implementation of neuroscience-inspired plasticity learning rules, and highlight performance on a suite of tasks. Our energy analysis confirms the value of the approach, as the learning budget stays below 20 $μJ$ even for large tasks used typically in machine learning.