When deep neural network (DNN) is extensively utilized for edge AI (Artificial Intelligence), for example, the Internet of things (IoT) and autonomous vehicles, it makes CMOS (Complementary Metal Oxide Semiconductor)-based conventional computers suffer from overly large computing loads. Memristor-based devices are emerging as an option to conduct computing in memory for DNNs to make them faster, much more energy efficient, and accurate. Despite having excellent properties, the memristor-based DNNs are yet to be commercially available because of Stuck-At-Fault (SAF) defects. A Mapping Transformation (MT) method is proposed in this paper to mitigate Stuck-at-Fault (SAF) defects from memristor-based DNNs. First, the weight distribution for the VGG8 model with the CIFAR10 dataset is presented and analyzed. Then, the MT method is used for recovering inference accuracies at 0.1% to 50% SAFs with two typical cases, SA1 (Stuck-At-One): SA0 (Stuck-At-Zero) = 5:1 and 1:5, respectively. The experiment results show that the MT method can recover DNNs to their original inference accuracies (90%) when the ratio of SAFs is smaller than 2.5%. Moreover, even when the SAF is in the extreme condition of 50%, it is still highly efficient to recover the inference accuracy to 80% and 21%. What is more, the MT method acts as a regulator to avoid energy and latency overhead generated by SAFs. Finally, the immunity of the MT Method against non-linearity is investigated, and we conclude that the MT method can benefit accuracy, energy, and latency even with high non-linearity LTP = 4 and LTD = −4.

Stuck-At-Fault (SAF) defect of memristor generated from immature fabrication and heavy device utilization makes neuromorphic computing systems commercially unavailable. To mitigate this problem, a Reconfigurable Mapping Algorithm (RMA) is proposed in this paper. Based on the analysis for the VGG8 model with CIFAR10 dataset, the experiment results show that the RMA is efficient in restoring the inference accuracy up to 90% (the original accuracy without SAF) under SAFs from 0.1% to 50%, where Stuck-At-One (SA1): Stuck-At-Zero (SA0) = 5:1, 1:5, and 1:1. Additionally, the RMA improves the accuracy more than 50% in presence of high nonlinearity LTP = 4 and LTD = -4 and the standard conductance drift (10 years at 85 degrees Celsius) nearly has no influence on the inference accuracy of the DNN with the RMA.

Counting the active node numbers is an essential parametric quantity as it is used for appraising the performance of a pragmatic network. Different conventional protocol based techniques can be used to determine this parametric quantity. However, these techniques have several limitations including protocol complexity in underwater environment due to the unique characteristics of underwater network such as long propagation delay, high error rate, non-negligible captures effect, dispersion, node mobility and high path loss. In order to evade those limitations a cross-correlation based node estimation approach is implicated. It is an alternative and a statistical approach for signal processing and it is also an efficient technique for any environment networks. In this piece of work, a node estimation technique is proposed by cross-correlating the received signals by four sensors for underwater networks. Nodes and sensors are considered as transmitters and receivers respectively. The aim of this work is to improve the estimation performance including accuracy compared to the performances of existing methods. Here, the performance is measured with respect to the comparison of coefficient of variance and error bar and it exhibits better performance comparing to the existing works.