Low-Latency Spiking Neural Networks Using Pre-Charged Membrane Potential and Delayed Evaluation.

Spiking neural networks (SNNs) have attracted many researchers' interests due to its biological plausibility and event-driven characteristic. In particular, recently, many studies on high-performance SNNs comparable to the conventional analog-valued neural networks (ANNs) have been reported by converting weights trained from ANNs into SNNs. However, unlike ANNs, SNNs have an inherent latency that is required to reach the best performance because of differences in operations of neuron. In SNNs, not only spatial integration but also temporal integration exists, and the information is encoded by spike trains rather than values in ANNs. Therefore, it takes time to achieve a steady-state of the performance in SNNs. The latency is worse in deep networks and required to be reduced for the practical applications. In this work, we propose a pre-charged membrane potential (PCMP) for the latency reduction in SNN. A variety of neural network applications (e.g., classification, autoencoder using MNIST and CIFAR-10 datasets) are trained and converted to SNNs to demonstrate the effect of the proposed approach. The latency of SNNs is successfully reduced without accuracy loss. In addition, we propose a delayed evaluation method (DE), by which the errors during the initial transient are discarded. The error spikes occurring in the initial transient is removed by DE, resulting in the further latency reduction. DE can be used in combination with PCMP for further latency reduction. Finally, we also show the advantages of the proposed methods in improving the number of spikes required to reach a steady-state of the performance in SNNs for energy-efficient computing.

Impact of the Sub-Resting Membrane Potential on Accurate Inference in Spiking Neural Networks.

Spiking neural networks (SNNs) are considered as the third generation of artificial neural networks, having the potential to improve the energy efficiency of conventional computing systems. Although the firing rate of a spiking neuron is an approximation of rectified linear unit (ReLU) activation in an analog-valued neural network (ANN), there remain many challenges to be overcome owing to differences in operation between ANNs and SNNs. Unlike actual biological and biophysical processes, various hardware implementations of neurons and SNNs do not allow the membrane potential to fall below the resting potential-in other words, neurons must allow the sub-resting membrane potential. Because there occur an excitatory post-synaptic potential (EPSP) as well as an inhibitory post-synaptic potential (IPSP), negatively valued synaptic weights in SNNs induce the sub-resting membrane potential at some time point. If a membrane is not allowed to hold the sub-resting potential, errors will accumulate over time, resulting in inaccurate inference operations. This phenomenon is not observed in ANNs given their use of only spatial synaptic integration, but it can cause serious performance degradation in SNNs. In this paper, we demonstrate the impact of the sub-resting membrane potential on accurate inference operations in SNNs. Moreover, several important considerations for a hardware SNN that can maintain the sub-resting membrane potential are discussed. All of the results in this paper indicate that it is essential for neurons to allow the sub-resting membrane potential in order to realize high-performance SNNs.

The Methodological Quality of Systematic Reviews and Meta-Analyses on the Effectiveness of Non-pharmacological Cancer Pain Management.

This study used the Assessment of Multiple Systematic Reviews (AMSTAR) to determine how the quality of methodologies in systematic reviews (SRs) and meta-analyses (MAs) impacts the effectiveness of nonpharmacological cancer pain management. The authors searched 11 electronic databases for published and unpublished studies (in English and Korean) on SRs and MAs relating to "cancer" and "pain management" that were released prior to May 7, 2014. The findings from 17 SRs and MAs were scored for quality using AMSTAR and coded by management type and value of effect size. Only one article was deemed high quality; five were considered to be of low quality. The mean score was 5.47 (SD = 2.03), indicating moderate quality. Among the items we tested via AMSTAR, zero studies stated whether they have a conflict of interest in their covered studies, but every study established the research question and inclusion criteria before constructing the review. Rigorous assessment of nonpharmacological cancer pain management using AMSTAR might contribute to healthcare providers making more informed clinical decisions when it comes to handling pain. Based on the finding, researchers should abide by reporting guidelines for SRs and MAs to ensure that research is more rigorously synthesized.