The increasing demand for continual learning in sequential data processing has led to progressively complex training methodologies and larger recurrent network architectures. Consequently, this has widened the knowledge gap between continual learning with recurrent neural networks (RNNs) and their ability to operate on devices with limited memory and compute. To address this challenge, we investigate the effectiveness of simplifying RNN architectures, particularly gated recurrent unit (GRU), and its impact on both single-task and multitask sequential learning. We propose a new variant of GRU, namely the minion recurrent unit (MiRU). MiRU replaces conventional gating mechanisms with scaling coefficients to regulate dynamic updates of hidden

An experimental and theoretical investigation of three phase direct contact heat transfer by evaporation of refrigerant drops in an immiscible liquid has been carried out. Refrigerant Rl2 and R134a were used for the dispersed phase, while water and brine were the immiscible continuous phase. A numerical analysis is presented to predict the temperature distribution throughout the circular test column radially and axially is achieved. Experimental measurements of the temperature distribution have been compared with the numerical results and are discussed .A comparison between the experimental and theoretical results showed acceptable agreement and applicability of the derived equations. Comparison with other related work showed similar beh

The paper aims to propose Teaching Learning based Optimization (TLBO) algorithm to solve 3-D packing problem in containers. The objective which can be presented in a mathematical model is optimizing the space usage in a container. Besides the interaction effect between students and teacher, this algorithm also observes the learning process between students in the classroom which does not need any control parameters. Thus, TLBO provides the teachers phase and students phase as its main updating process to find the best solution. More precisely, to validate the algorithm effectiveness, it was implemented in three sample cases. There was small data which had 5 size-types of items with 12 units, medium data which had 10 size-types of items w

Precise forecasting of pore pressures is crucial for efficiently planning and drilling oil and gas wells. It reduces expenses and saves time while preventing drilling complications. Since direct measurement of pore pressure in wellbores is costly and time-intensive, the ability to estimate it using empirical or machine learning models is beneficial. The present study aims to predict pore pressure using artificial neural network. The building and testing of artificial neural network are based on the data from five oil fields and several formations. The artificial neural network model is built using a measured dataset consisting of 77 data points of Pore pressure obtained from the modular formation dynamics tester. The input variables

AA wahid, journal mustansiriyah of sports science, 2023

Frictional heat is generated when the clutch starts to engag. As a result of this operation the surface temperature is increased rapidly due to the difference in speed between the driving and driven parts. The influence of the thickness of frictional facing on the distribution of the contact pressure of the multi-disc clutches has been investigated using a numerical approach (the finite element method). The analysis of contact problem has been carried out for a multiple disc dry clutch (piston, clutch discs, separators and pressure plate). The results present the distribution of the contact pressure on all tShe surfaces of friction discs that existed in the friction clutch system. Axisymmetric finite element models have been developed to ac

The seasonal behavior of the light curve for selected star SS UMI and EXDRA during outburst cycle is studied. This behavior describes maximum temperature of outburst in dwarf nova. The raw data has been mathematically modeled by fitting Gaussian function based on the full width of the half maximum and the maximum value of the Gaussian. The results of this modeling describe the value of temperature of the dwarf novae star system leading to identify the type of elements that each dwarf nova consisted of.

In this research, Artificial Neural Networks (ANNs) technique was applied in an attempt to predict the water levels and some of the water quality parameters at Tigris River in Wasit Government for five different sites. These predictions are useful in the planning, management, evaluation of the water resources in the area. Spatial data along a river system or area at different locations in a catchment area usually have missing measurements, hence an accurate prediction. model to fill these missing values is essential.
The selected sites for water quality data prediction were Sewera, Numania , Kut u/s, Kut d/s, Garaf observation sites. In these five sites models were built for prediction of the water level and water quality parameters.