In a recent article we described a new type of deep neural network– a Perpetual Learning Machine (PLM) – which is capable of learning ‘on the fly’ like a brain by existing in a state of Perpetual Stochastic Gradient Descent (PSGD). Here, by simulating the process of practice, we demonstrate both selective memory and selective forgetting when we introduce statistical recall biases during PSGD. F...

in this work, nanostructured niti shape memory alloy with equal atomic percentage was produced through mechanical alloying. the result exhibited that after 60 h of mechanical alloying of high purity elemental powder mixtures of nickel and titanium by a planetary high-energy ball mill, the ti dissolved into ni lattice and niti (b2) phase with was obtained. the xrd investigations, sem observation...

In this paper one of the important “end of life options” (remanufacturing) has been analysed. Among the related studies surveyed the various remanufacturing aspects, less attention has been paid to the stochastic process routing. In this regard, a remanufacturing process routing with stochastic activities is modelled as a GERT network. One of the efficient ways to analyse a remanufacturing proc...

The main goal of this paper is to give a rigorous mathematical description of systems for processing quantum information. To do it authors consider abstract state machines as models of classical computational systems. This class of machines is refined by introducing constrains on a state structure, namely, it is assumed that state of computational process has two components: a control unit stat...

In this paper, we consider a continuous-time autoregressive fractionally integrated moving average (CARFIMA) model, which is defined as the stationary solution of a stochastic differential equation driven by a standard fractional Brownian motion. Like the discrete-time ARFIMA model, the CARFIMA model is useful for studying time series with short memory, long memory and antipersistence. We inves...