AA wahid, journal mustansiriyah of sports science, 2023

In the presence of deep submicron noise, providing reliable and energy‐efficient network on‐chip operation is becoming a challenging objective. In this study, the authors propose a hybrid automatic repeat request (HARQ)‐based coding scheme that simultaneously reduces the crosstalk induced bus delay and provides multi‐bit error protection while achieving high‐energy savings. This is achieved by calculating two‐dimensional parities and duplicating all the bits, which provide single error correction and six errors detection. The error correction reduces the performance degradation caused by retransmissions, which when combined with voltage swing reduction, due to its high error detection, high‐energy savings are achieved. The res

A three-stage learning algorithm for deep multilayer perceptron (DMLP) with effective weight initialisation based on sparse auto-encoder is proposed in this paper, which aims to overcome difficulties in training deep neural networks with limited training data in high-dimensional feature space. At the first stage, unsupervised learning is adopted using sparse auto-encoder to obtain the initial weights of the feature extraction layers of the DMLP. At the second stage, error back-propagation is used to train the DMLP by fixing the weights obtained at the first stage for its feature extraction layers. At the third stage, all the weights of the DMLP obtained at the second stage are refined by error back-propagation. Network structures an

This paper is concerned with introducing and studying the o-space by using out degree system (resp. i-space by using in degree system) which are the core concept in this paper. In addition, the m-lower approximations, the m-upper approximations and ospace and i-space. Furthermore, we introduce near supraopen (near supraclosed) d. g.'s. Finally, the supra-lower approximation, supraupper approximation, supra-accuracy are defined and some of its properties are investigated.