A simple and efficient SNN and its performance & robustness evaluation method to enable hardware implementation
This work addresses the challenge of translating SNNs into hardware for brain-like computing, though it appears incremental as it builds on existing SNN methods with efficiency gains.
The authors tackled the complexity of Spiking Neural Networks (SNNs) for hardware implementation by developing a simple 2-layered network that achieves state-of-the-art performance on standard datasets with improved efficiency, such as using 3x fewer neurons and 30x fewer training epochs for Fisher Iris classification, and introduced a computationally efficient evaluation method with 0.98 correlation.
Spiking Neural Networks (SNN) are more closely related to brain-like computation and inspire hardware implementation. This is enabled by small networks that give high performance on standard classification problems. In literature, typical SNNs are deep and complex in terms of network structure, weight update rules and learning algorithms. This makes it difficult to translate them into hardware. In this paper, we first develop a simple 2-layered network in software which compares with the state of the art on four different standard data-sets within SNNs and has improved efficiency. For example, it uses lower number of neurons (3 x), synapses (3.5 x) and epochs for training (30 x) for the Fisher Iris classification problem. The efficient network is based on effective population coding and synapse-neuron co-design. Second, we develop a computationally efficient (15000 x) and accurate (correlation of 0.98) method to evaluate the performance of the network without standard recognition tests. Third, we show that the method produces a robustness metric that can be used to evaluate noise tolerance.