Hybrid neural network

About: Hybrid neural network is a research topic. Over the lifetime, 1305 publications have been published within this topic receiving 18223 citations.

Learning Recursive Filters for Low-Level Vision via a Hybrid Neural Network

Abstract: In this paper, we consider numerous low-level vision problems (e.g., edge-preserving filtering and denoising) as recursive image filtering via a hybrid neural network. The network contains several spatially variant recurrent neural networks (RNN) as equivalents of a group of distinct recursive filters for each pixel, and a deep convolutional neural network (CNN) that learns the weights of RNNs. The deep CNN can learn regulations of recurrent propagation for various tasks and effectively guides recurrent propagation over an entire image. The proposed model does not need a large number of convolutional channels nor big kernels to learn features for low-level vision filters. It is significantly smaller and faster in comparison with a deep CNN based image filter. Experimental results show that many low-level vision tasks can be effectively learned and carried out in real-time by the proposed algorithm.

Teaching learning optimization and neural network for the effective prediction of heat transfer rates in tube heat exchangers

Abstract: Heat exchangers are widely used in many field for the purpose of heat from one medium to another. In heat exchanger one or more fluids are used, and which are various types based on its flow and construction. Design of heat exchanger is one of the important field, in the research due to its application. In recent decade the simulation is used in most of the engineering application. A proper simulation technique can effectively analysis the functionality and behavior of any machine before its construction or production. In this sense the machine learning techniques are used in some simulation analysis to model the machine or engine. In this work we used a hybrid neural network for the modeling of shell and tube type heat exchanger and its heat transfer rate is predicted effectively. The computational performance of the proposed technique is compared with the conventional technique and it is proved the effectiveness of the hybrid machine learning technique.

A Hybrid Neural Network - World Cup Optimization Algorithm for Melanoma Detection.

Abstract: One of the most dangerous cancers in humans is Melanoma. However, early detection of melanoma can help us to cure it completely. This paper presents a new efficient method to detect malignancy in melanoma via images. At first, the extra scales are eliminated by using edge detection and smoothing. Afterwards, the proposed method can be utilized to segment the cancer images. Finally, the extra information is eliminated by morphological operations and used to focus on the area which melanoma boundary potentially exists. To do this, World Cup Optimization algorithm is utilized to optimize an MLP neural Networks (ANN). World Cup Optimization algorithm is a new meta-heuristic algorithm which is recently presented and has a good performance in some optimization problems. WCO is a derivative-free, Meta-Heuristic algorithm, mimicking the world's FIFA competitions. World cup Optimization algorithm is a global search algorithm while gradient-based back propagation method is local search. In this proposed algorithm, multi-layer perceptron network (MLP) employs the problem's constraints and WCO algorithm attempts to minimize the root mean square error. Experimental results show that the proposed method can develop the performance of the standard MLP algorithm significantly.