Neuromorphic hardware improves speech recognition with input-dependent gating
Input-dependent Neuromodulation Enhances Mixed-Signal Neuromorphic Hardware
Neural and Evolutionary ComputingEmerging Technologies
Summary
Small brain-inspired computer chips, called neuromorphic processors, are good at running neural networks efficiently but face limits in size and precision. This paper shows that adding a way for the chip to adjust how it processes data depending on what input it sees greatly improves accuracy in recognizing spoken digits. The authors demonstrate this by using a small off-chip module to guide the chip’s internal parameters dynamically during operation. This method raised the chip’s speech recognition accuracy by over 17 percentage points across multiple test setups.
What this means in practice
- •For embedded device engineers: Improve speech recognition accuracy on small, low-power neuromorphic chips by adding dynamic input-dependent parameter adjustments.
- •For audio processing developers: Enhance on-device spoken digit classification by integrating input-dependent neuromodulation in neuromorphic systems.
Authors
Aashman Mehta, AbdelQader AlKilany, Dan F. M. Goodman, Giacomo Indiveri, Melika Payvand
Abstract
Gating mechanisms allow a fixed neural network to adapt its computation to the current input by dynamically modulating its effective parameters. In the brain, neuromodulation uses this principle to move neural circuits between dynamical regimes, and deep learning exploits input-dependent gating, e.g., in gated recurrent networks and self-attention. Input-dependent modulation has also recently been shown to improve spiking neural networks, with particularly strong benefits in small, parameter-limited ones. This makes neuromodulation especially promising for neuromorphic processors at the edge, where area, memory and energy budgets constrain network size, while circuit physics limits parameter precision. Here we demonstrate input-dependent, within-trial neuromodulation of a spiking recurrent neural network on a mixed-signal neuromorphic processor. An off-chip modulator reads the on-chip network's input and activity and adjusts its population-level gains while the chip's analog circuits compute with the physics of the silicon. Neuromodulation raises binary spoken-digit classification accuracy by $+17.3 \pm 10.4$ percentage points, tested across five hardware network instantiations.