SEENN: Towards Temporal Spiking Early-Exit Neural Networks

04/02/2023
by   Yuhang Li, et al.
0

Spiking Neural Networks (SNNs) have recently become more popular as a biologically plausible substitute for traditional Artificial Neural Networks (ANNs). SNNs are cost-efficient and deployment-friendly because they process input in both spatial and temporal manners using binary spikes. However, we observe that the information capacity in SNNs is affected by the number of timesteps, leading to an accuracy-efficiency tradeoff. In this work, we study a fine-grained adjustment of the number of timesteps in SNNs. Specifically, we treat the number of timesteps as a variable conditioned on different input samples to reduce redundant timesteps for certain data. We call our method Spiking Early-Exit Neural Networks (SEENNs). To determine the appropriate number of timesteps, we propose SEENN-I which uses a confidence score thresholding to filter out the uncertain predictions, and SEENN-II which determines the number of timesteps by reinforcement learning. Moreover, we demonstrate that SEENN is compatible with both the directly trained SNN and the ANN-SNN conversion. By dynamically adjusting the number of timesteps, our SEENN achieves a remarkable reduction in the average number of timesteps during inference. For example, our SEENN-II ResNet-19 can achieve 96.1 an average of 1.08 timesteps on the CIFAR-10 test dataset.

READ FULL TEXT
research
05/27/2023

Input-Aware Dynamic Timestep Spiking Neural Networks for Efficient In-Memory Computing

Spiking Neural Networks (SNNs) have recently attracted widespread resear...
research
02/25/2020

RMP-SNNs: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Networks

Spiking Neural Networks (SNNs) have recently attracted significant resea...
research
04/28/2018

Spiking Deep Residual Network

Recently, spiking neural network (SNN) has received significant attentio...
research
05/14/2022

Spiking Approximations of the MaxPooling Operation in Deep SNNs

Spiking Neural Networks (SNNs) are an emerging domain of biologically in...
research
07/31/2022

Ultra-low Latency Adaptive Local Binary Spiking Neural Network with Accuracy Loss Estimator

Spiking neural network (SNN) is a brain-inspired model which has more sp...
research
03/17/2023

Unleashing the Potential of Spiking Neural Networks by Dynamic Confidence

This paper presents a new methodology to alleviate the fundamental trade...
research
05/28/2018

Sacrificing Accuracy for Reduced Computation: Cascaded Inference Based on Softmax Confidence

We study the tradeoff between computational effort and accuracy in a cas...

Please sign up or login with your details

Forgot password? Click here to reset