Optimizing the Consumption of Spiking Neural Networks with Activity Regularization
This work addresses energy efficiency for edge computing applications, but it is incremental as it builds on existing DNN-to-SNN conversion methods.
The paper tackled the problem of high energy consumption in Spiking Neural Networks (SNNs) on edge devices by enforcing sparsity in activation maps using training regularizers, resulting in optimized DNNs and SNNs with reduced synaptic operations.
Reducing energy consumption is a critical point for neural network models running on edge devices. In this regard, reducing the number of multiply-accumulate (MAC) operations of Deep Neural Networks (DNNs) running on edge hardware accelerators will reduce the energy consumption during inference. Spiking Neural Networks (SNNs) are an example of bio-inspired techniques that can further save energy by using binary activations, and avoid consuming energy when not spiking. The networks can be configured for equivalent accuracy on a task through DNN-to-SNN conversion frameworks but their conversion is based on rate coding therefore the synaptic operations can be high. In this work, we look into different techniques to enforce sparsity on the neural network activation maps and compare the effect of different training regularizers on the efficiency of the optimized DNNs and SNNs.