Quantized Context Based LIF Neurons for Recurrent Spiking Neural Networks in 45nm
This work addresses efficiency and scalability for neuromorphic computing applications, representing an incremental improvement in hardware design for spiking neural networks.
The study tackled hardware implementation of a recurrent spiking neural network by proposing a quantized context-dependent neuron model, achieving 90% accuracy on a gesture classification dataset with a compact 900um^2 design in 45nm technology.
In this study, we propose the first hardware implementation of a context-based recurrent spiking neural network (RSNN) emphasizing on integrating dual information streams within the neocortical pyramidal neurons specifically Context- Dependent Leaky Integrate and Fire (CLIF) neuron models, essential element in RSNN. We present a quantized version of the CLIF neuron (qCLIF), developed through a hardware-software codesign approach utilizing the sparse activity of RSNN. Implemented in a 45nm technology node, the qCLIF is compact (900um^2) and achieves a high accuracy of 90% despite 8 bit quantization on DVS gesture classification dataset. Our analysis spans a network configuration from 10 to 200 qCLIF neurons, supporting up to 82k synapses within a 1.86 mm^2 footprint, demonstrating scalability and efficiency