Research has shown a strong correlation between the topology and functional capability of neural networks, though difficulties encountered in traditional neural network design and training increase in relation to the size and complexity of the network. Constructing a neural network topology through the integration of modularized, functional sub-networks has been shown to provide a reduction in ...

Research has shown a strong correlation between the topology and functional capability of neural networks, though difficulties encountered in traditional neural network design and training increase in relation to the size and complexity of the network. Constructing a neural network topology through the integration of modularized, functional sub-networks has been shown to provide a reduction in ...

This paper proposes a methodology for the layout selection of an urban drainage system as extension to optimal sewer network design proposed by Duque, Aguilar, & Saldarriaga. The approach in this uses objective function that takes into account all input data problem, such as: land topography, street topology, and inflow each manhole. Once is selected, optimally designed using dynamic progra...

Nowadays, lightweight automotive component design, regarding fuel consumption, environmental pollutants and manufacturing costs, is one of the main issues in the automotive societies. In addition, considering safety reasons, the durability of the automotive components, as one of the most important design requirements should be guaranteed. In this paper, a two-step optimization process including...

Generative modeling techniques are being rapidly developed in the field of deep learning, and they have been applied to topology optimization. The variational autoencoder (VAE) is a generative modeling technology that extends the autoencoder to generate new images with a limited latent space. We modified the basic VAE structure to encode optimization conditions and decode latent variables for t...

This paper presents a new heuristic algorithm useful for long-term planning of survivable WDM networks. A multi-period model is formulated that combines network topology design and capacity expansion. The ability to determine network expansion schedules of this type becomes increasingly important to the telecommunications industry and to its customers. The solution technique consists of a Genet...

The packet switching based Network-on-Chip (NoC) is an obvious interconnect design alternative to the shared bus, crossbar or ring based on-chip communication architecture used in System-on-Chips (SoCs). The advent of the three dimensional NoC (3D NoC) architecture attracts added interest as it offers improved performance and shorter global interconnect. In the 3D NoC architecture, topology pla...

In Nature, the primary goal of any network is to survive. This is less obvious for engineering networks (electric power, gas, water, transportation systems etc.) that are expected to operate under normal conditions most of time. As a result, the ability of a network to withstand massive sudden damage caused by adverse events (or survivability) has not been among traditional goals in the network...

OSPF, or Open Shortest Path First, is a commonly used interior gateway protocol. An integer weight is assigned to each arc and the entire network topology and arc weights are known to each router. Each router computes a graph of shortest weight paths from itself to every other router in the network. Traffic is routed on the shortest weight paths. All traffic leaving router s with destination ro...