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.

A hybrid neural network- meta heuristics approach for permutation flow shop scheduling problems

Abstract: The objective of this study is to find a sequence of jobs for the permutation flow shop to minimize makespan. A feed forward back propagation neural network is used to solve the 10 machine problem taken from the literature. The network is trained with the optimal sequences for five, six and seven jobs problem. This trained network is then used to solve the problem with greater number of jobs. The sequence obtained using neural network is used to generate initial population for genetic algorithm (ANN-GA), genetic algorithm using Random Insertion Perturbation Scheme (ANN-GA-RIPS) and Simulated Annealing (ANN-SA). Makespans obtained through these approaches are compared with the Taillard's benchmark problems.

Self-organizing neural network for motion detection by a moving observer

Abstract: The ability to rapidly detect moving objects while dynamically exploring a work environment is an essential characteristic of any active vision system. However, many of the proposed computer vision paradigms are unable to efficiently deal with the complexities of real world situations because they employ algorithms that attempt to accurately reconstruct structure- from-motion. An alternative view is to employ algorithms that only compute the minimal amount of information necessary to solve the task at hand. One method of qualitatively detecting independently moving objects by a moving camera (or observer) is based on the notion that the projected velocity of any point on a spherical image is constrained to lie on a one-dimensional locus in a local 2-D velocity space. The velocities along this locus, called a constraint ray, correspond to the rotational and translational motion of the observer. If the observer motion is known a priori, then any object moving independently through the rigid 3- D environment will exhibit a projected velocity that does not fall on this locus. As a result, the independently moving object can be detected using a clustering algorithm. In this paper, a hybrid neural network architecture is proposed for discriminating between flow velocities that are caused by camera movement and by object motion. The computing architecture is essentially a two stage process. In the first stage, a self-organizing neural network is used to learn the constraint parameters associated with typical observer movements by moving the camera apparatus through a stationary environment. Once the observer movements have been adequately learned by the self-organizing neural network, the corresponding synaptic weight values are used to program a modified radial basis function (RBF) network. During the second stage, the RBF network architecture acts as a constraint region classifier by employing clustering strategies to label incomplete motion field information (i.e. the velocity component that is parallel to the spatial gradient).© (1994) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Supervised classification method based on hybrid neural network

Abstract: The invention relates to a supervised classification method, in particular to a supervised classification method based on a hybrid neural network, and belongs to the technical field of computers and information science. The method comprises the following steps of completing initialization of data division by using a K-means algorithm; training a local NN model; using an EM algorithm to jointly optimize the gating function and the expert model; updating the gate control network parameters through SGD, re-dividing the data, and using the newly-divided data subsets for retraining the local NN model; repeating the above steps until convergence. According to the supervised classification method provided by the invention, the hybrid neural network is fused to supervised classification, so that the data with heterogeneity are divided into a plurality of homogeneous data subsets, a local expert model is learned in each subset, the classification accuracy is effectively improved, and the classification accuracy is superior to that of most other supervised classification algorithms.

A Fully Spiking Hybrid Neural Network for Energy-Efficient Object Detection

Abstract: This paper proposes a Fully Spiking Hybrid Neural Network (FSHNN) for energy-efficient and robust object detection in resource-constrained platforms. The network architecture is based on Convolutional SNN using leaky-integrate-fire neuron models. The model combines unsupervised Spike Time-Dependent Plasticity (STDP) learning with back-propagation (STBP) learning methods and also uses Monte Carlo Dropout to get an estimate of the uncertainty error. FSHNN provides better accuracy compared to DNN based object detectors while being 150X energy-efficient. It also outperforms these object detectors, when subjected to noisy input data and less labeled training data with a lower uncertainty error.

Analog Circuit Fault Diagnosis Based on Principal Component Analysis of Pretreatment and Particle Swarm Hybrid Neural Network

Abstract: With the rapid development of electronic technology, the system reliability and economic requirements of the importance of the analog circuit fault diagnosis has become increasingly prominent. Aiming at the shortcomings of traditional diagnosis method, the paper presents an analog circuit fault diagnosis method based on principal component analysis of pretreatment and particle swarm hybrid neural network. The method adopts hybrid algorithm to adjust the network weights and thresholds to avoid falling into the local minimum value, which uses principal component pretreatment effectively reduce the complexity of calculation. Simulation results show that the diagnostic method can be used for tolerance analog circuit fault diagnosis, has better application prospect.