Search

A spiking neural network (SNN) is a type of artificial neural network that operates based on discrete spikes to process timing information, similar to the manner in which the human brain processes real-world problems. In this paper, we propose a new spiking neural network (SNN) based on conventional, biologically plausible paradigms, such as the leaky integrate-and-fire model, spike timing-dependent plasticity, and the adaptive spiking threshold, by suggesting new biological models; that is, dynamic inhibition weight change, a synaptic wiring method, and Bayesian inference. The proposed network is designed for image recognition tasks, which are frequently used to evaluate the performance of conventional deep neural networks. To manifest the bio-realistic neural architecture, the learning is unsupervised, and the inhibition weight is dynamically changed; this, in turn, affects the synaptic wiring method based on Hebbian learning and the neuronal population. In the inference phase, Bayesian inference successfully classifies the input digits by counting the spikes from the responding neurons. The experimental results demonstrate that the proposed biological model ensures a performance improvement compared with other biologically plausible SNN models.

This study investigates the effect of annealing on the mechanical properties of fused deposition modeling (FDM) 3D-printed recycled carbon fiber (rCF)-reinforced composites. In this study, filaments for FDM 3D printers are self-fabricated from pure acrylonitrile butadiene styrene (ABS) and ABS reinforced with fiber content of 10 wt% and 20 wt% rCF. This study explores the tensile and flexural properties as a function of the annealing temperature and time for the three different fiber content values. In addition, dimensional measurements of the shape changes are performed to determine the suitability of applying annealing in practical manufacturing processes. The results show that annealing improves the mechanical properties by narrowing the voids between the beads, which occur during the FDM process, and by reducing the gaps between the fibers and polymer. Following annealing, the largest tensile and flexural strength improvements are 12.64% and 42.33%, respectively, for the 20 wt% rCF content samples. Moreover, compared with the pure ABS samples, the annealing effect improves the mechanical properties of the rCF-reinforced samples more effectively, and they have higher dimensional stability, indicating their suitability for annealing. These results are expected to expand the application fields of rCF and greatly increase the potential use of FDM-printed parts.