Topic
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.
Papers published on a yearly basis
Papers
More filters
TL;DR: Results showed that the proposed EFHNN can be deployed effectively to achieve optimal mapping of input factors and project success output and was significantly better than the performance achieved by previous models that used singular linear NN.
33 citations
TL;DR: An effective segmentation-free approach using a hybrid neural network hidden Markov model (NN-HMM) for offline handwritten Chinese text recognition (HCTR) and a deep convolutional neural network with automatically learned discriminative features demonstrates its superiority in the HMM framework.
Abstract: This paper proposes an effective segmentation-free approach using a hybrid neural network hidden Markov model (NN-HMM) for offline handwritten Chinese text recognition (HCTR). In the general Bayesian framework, the handwritten Chinese text line is sequentially modeled by HMMs with each representing one character class, while the NN-based classifier is adopted to calculate the posterior probability of all HMM states. The key issues in feature extraction, character modeling, and language modeling are comprehensively investigated to show the effectiveness of NN-HMM framework for offline HCTR. First, a conventional deep neural network (DNN) architecture is studied with a well-designed feature extractor. As for the training procedure, the label refinement using forced alignment and the sequence training can yield significant gains on top of the frame-level cross-entropy criterion. Second, a deep convolutional neural network (DCNN) with automatically learned discriminative features demonstrates its superiority to DNN in the HMM framework. Moreover, to solve the challenging problem of distinguishing quite confusing classes due to the large vocabulary of Chinese characters, NN-based classifier should output 19900 HMM states as the classification units via a high-resolution modeling within each character. On the ICDAR 2013 competition task of CASIA-HWDB database, DNN-HMM yields a promising character error rate (CER) of 5.24% by making a good trade-off between the computational complexity and recognition accuracy. To the best of our knowledge, DCNN-HMM can achieve a best published CER of 3.53%.
33 citations
TL;DR: A hybrid neural network model for solving optimization problems is proposed, where an energy function which contains the constraints and cost criteria of an optimization problem is derived, and the neural network is used to find the global minimum of the energy function, which corresponds to a solution of the optimization problem.
Abstract: A hybrid neural network model for solving optimization problems is proposed. An energy function which contains the constraints and cost criteria of an optimization problem is derived, and then the neural network is used to find the global minimum (or maximum) of the energy function, which corresponds to a solution of the optimization problem. The network contains two subnets: a constraint network and a goal network. The constraint network models the constraints of an optimization problem and computes the gradient (updating) value of each neuron such that the energy function monotonically converges to satisfy all constraints of the problem. The goal network points out the direction of convergence for finding an optimal value for the cost criteria. These two subnets ensure that the neural network finds feasible as well as optimal (or near-optimal) solutions. The traveling salesman problem and the Hamiltonian cycle problem are used to demonstrate the method. >
32 citations
Proceedings Article•
01 Jan 1992
TL;DR: A hybrid multilayer perceptron (MLP)/hidde arkov model (HMM) speaker-independent continuous-speech recogni-b tion system, in which the advantages of both approaches are combined using MLPs to estimate the state-dependent observation probabilities of an HMM.
Abstract: n M In this paper we present a hybrid multilayer perceptron (MLP)/hidde arkov model (HMM) speaker-independent continuous-speech recogni-b tion system, in which the advantages of both approaches are combined y using MLPs to estimate the state-dependent observation probabilities p of an HMM. New MLP architectures and training procedures are resented which allow the modeling of multiple distributions for phonetic a p classes and context-dependent phonetic classes. Comparisons with ure HMM system illustrate advantages of the hybrid approach both in terms of recognition accuracy and number of parameters required.
32 citations
TL;DR: A hybrid system based on neural network (NN) and immune co-evolutionary algorithm (ICEA) to predict the fit of the garments and search optimal sizes and the algorithms can be incorporated into garment computer-aided design system.
Abstract: The purpose of this study was to develop a system to utilize the successful experiences and help the beginners of garment pattern design (GPD) through optimization methods. Size design of fit garme...
32 citations