RECURRENT NEURAL NETWORK-BASED PORTFOLIO INVESTMENT

Instead of existing methods,a recurrent neural network is conceived to deal with three stages of portfolio management.Mainly,a deterministic annealing neural network is proposed for the approach to portfolio problem,which is a kind of quadratic programming.Finally,through a real example,we verify that the neural network model proposed in this paper is a good tool to solve the portfolio problem.

Recent Implementations in LASP 3.0:Global Neural Network Potential with Multiple Elements and Better Long-Range Description

LASP(large-scale atomistic simulation with neural network potential)software developed by our group since 2018 is a powerful platform(www.lasphub.com)for performing atomic simulation of complex materials.The software integrates the neural network(NN)potential technique with the global potential energy surface exploration method,and thus can be utilized widely for structure prediction and reaction mechanism exploration.Here we introduce our recent update on the LASP program version 3.0,focusing on the new functionalities including the advanced neuralnetwork training based on the multi-network framework,the newly-introduced S^(7) and S^(8) power type structure descriptor(PTSD).These new functionalities are designed to further improve the accuracy of potentials and accelerate the neural network training for multipleelement systems.Taking Cu-C-H-O neural network potential and a heterogeneous catalytic model as the example,we show that these new functionalities can accelerate the training of multi-element neural network potential by using the existing single-network potential as the input.The obtained double-network potential Cu CHO is robust in simulation and the introduction of S^(7) and S^(8) PTSDs can reduce the root-mean-square errors of energy by a factor of two.

APPLICATIONS OF FAST SIMULATED ANNEALING IN NEURAL NETWORKS

Fast simulated annealing is implemented into the learning process of neural network to replace the traditional back-propagation algorithm. The new procedure exhibits performance fast in learning and accurate in prediction compared to the traditional neural networks. Two numerical data sets were used to illustrate its use in chemistry.

Urban Growth Modeling Using Neural Network Simulation: A Case Study of Dongguan City, China

Dongguan is an important industrial city, located in the Pearl River Delta, South China. Recently, Dongguan city experienced a rapid urban growth with the locational advantage by transforming from traditional agricultural region to modern manufacturing metropolis. The urban transformation became the usual change in China under the background of urbanization which belongs to one trend of globalization in the 21st century. This paper tries to analyze urban growth simulation based on remotely sensed data of previous years and the related physical and socio-economic factors and predict future urban growth in 2024. The study examined and compared the land use/cover (LUC) changes over time based on produced maps of 2004, 2009, and 2014. The results showed that water and forest area decreased since the past years. In contrast, the urban land increased from 2004 to 2014, and this increasing trend will continue to the future years through the urbanization process. Having understood the spatiotemporal trends of urban growth, the study simulated the urban growth of Dongguan city for 2024 using neural network simulation technique. Further, the figure of merit (FoM) of simulated map of 2014 map was 8.86%, which can be accepted in the simulation and used in the prediction process. Based on the consideration of water body and forest, the newly growth area is located in the west, northeast, and southeast regions of Dongguan city. The finding can help us to understand which areas are going to be considered in the future urban planning and policy by the local government.

Warpage and Shrinkage Optimization of Injection-Molded Plastic Spoon Parts for Biodegradable Polymers Using Taguchi, ANOVA and Artificial Neural Network Methods

In this study, it is attempted to give an insight into the injection processability of three self-prepared polymers from A to Z. This work presents material analysis, injection molding simulation, design of ex- periments alongside considering all interaction effects of controlling parameters carefully for green biodegradable polymeric systems, including polylactic acid （PLA）, polylactic acid-thermoplastic poly- urethane （PLA-TPU） and polylactic acid-thermoplastic starch （PLA-TPS）. The experiments were carried out using injection molding simulation software Autodesk Moldflov~~ in order to minimize warpage and volumetric shrinkage for each of the mentioned systems. The analysis was conducted by changing five significant processing parameters, including coolant temperature, packing time, packing pressure, mold temperature and melt temperature. Taguchi＇s [.27 （35） orthogonal array was selected as an efficient method for design of simulations in order to consider the interaction effects of the parameters and reduce spu- rious simulations. Meanwhile, artificial neural network （ANN） was also used for pattern recognition and optimization through modifying the processing conditions. The Taguchi coupled analysis of variance （ANOVA） and ANN analysis resulted in definition of optimum levels for each factor by two completely different methods. According to the results, melting temperature, coolant temperature and packing time had significant influence on the shrinkage and warpage. The ANN optimal level selection for minimiza- tion of shrinkage and/or warpage is in good agreement with ANOVA optimal level selection results. This investigation indicates that PLA-TPU compound exhibits the highest resistance to warpage and shrink- age defects compared to the other studied compounds.