Search

Abstract The paramount concern of highly accurate energy-efficient computing in machines with significant cognitive capabilities aims to enhance the accuracy and efficiency of bio-inspired Spiking Neural Networks (SNNs). This paper addresses this main objective by introducing a novel spatial power spike-timing-dependent plasticity (Spatial-Pow-STDP) learning rule as a digital block with high accuracy in a bio-inspired SNN model. Motivated by the demand for precise and accelerated computation that reduces high-cost resources in neural network applications, this paper presents a methodology based on COordinate Rotation DIgital Computer (CORDIC) definitions. The proposed designs of CORDIC algorithms for exponential (Exp CORDIC), natural logarithm (Ln CORDIC), and arbitrary power function (Pow CORDIC) are meticulously detailed and evaluated to ensure optimal acceleration and accuracy, which respectively show average errors near 10–9, 10–6, and 10–5 with 4, 4, and 6 iterations. The engineered architectures for the Exp, Ln, and Pow CORDIC implementations are illustrated and assessed, showcasing the efficiency achieved through high frequency, leading to the introduction of a Spatial-Pow-STDP learning block design based on Pow CORDIC that facilitates efficient and accurate hardware computation with 6.93 × 10–3 average error with 9 iterations. The proposed learning mechanism integrates this structure into a large-scale spatiotemporal SNN consisting of three layers with reduced hyper-parameters, enabling unsupervised training in an event-based paradigm using excitatory and inhibitory synapses. As a result, the application of the developed methodology and equations in the computational SNN model for image classification reveals superior accuracy and convergence speed compared to existing spiking networks by achieving up to 97.5%, 97.6%, 93.4%, and 93% accuracy, respectively, when trained on the MNIST, EMNIST digits, EMNIST letters, and CIFAR10 datasets with 6, 2, 2, and 6 training epochs.

Abstract Background Melatonin is a multi-functional molecule widely employed in order to mitigate abiotic stress factors, in general and salt stress in particular. Even though previous reports revealed that melatonin could exhibit roles in promoting seed germination and protecting plants during various developmental stages of several plant species under salt stress, no reports are available with respect to the regulatory acts of melatonin on the physiological and biochemical status as well as the expression levels of defense- and secondary metabolism-related related transcripts in bitter melon subjected to the salt stress. Results Herewith the present study, we performed a comprehensive analysis of the physiological and ion balance, antioxidant system, as well as transcript analysis of defense-related genes (WRKY1, SOS1, PM H + -ATPase, SKOR, Mc5PTase7, and SOAR1) and secondary metabolism-related gene expression (MAP30, α-MMC, polypeptide-P, and PAL) in salt-stressed bitter melon (Momordica charantia L.) plants in response to melatonin treatment. In this regard, different levels of melatonin (0, 75 and 150 µM) were applied to mitigate salinity stress (0, 50 and 100 mM NaCl) in bitter melon. Accordingly, present findings revealed that 100 mM salinity stress decreased growth and photosynthesis parameters (SPAD, Fv/Fo, Y(II)), RWC, and some nutrient elements (K+, Ca2+, and P), while it increased Y(NO), Y(NPQ), proline, Na+, Cl−, H2O2, MDA, antioxidant enzyme activity, and lead to the induction of the examined genes. However, prsiming with 150 µM melatonin increased SPAD, Fv/Fo, Y(II)), RWC, and K+, Ca2+, and P concentration while decreased Y(NO), Y(NPQ), Na+, Cl−, H2O2, and MDA under salt stress. In addition, the antioxidant system and gene expression levels were increased by melatonin (150 µM). Conclusions Overall, it can be postulated that the application of melatonin (150 µM) has effective roles in alleviating the adverse impacts of salinity through critical modifications in plant metabolism.