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.

Approximating support vector machine with artificial neural network for fast prediction

Abstract: Support vector machine (SVM) is a powerful algorithm for classification and regression problems and is widely applied to real-world applications. However, its high computational load in the test phase makes it difficult to use in practice. In this paper, we propose hybrid neural network (HNN), a method to accelerate an SVM in the test phase by approximating the SVM. The proposed method approximates the SVM using an artificial neural network (ANN). The resulting regression function of the ANN replaces the decision function or the regression function of the SVM. Since the prediction of the ANN requires significantly less computation than that of the SVM, the proposed method yields faster test speed. The proposed method is evaluated by experiments on real-world benchmark datasets. Experimental results show that the proposed method successfully accelerates SVM in the test phase with little or no prediction loss.

Neural networks for distant speech recognition

Abstract: Distant conversational speech recognition is challenging owing to the presence of multiple, overlapping talkers, additional non-speech acoustic sources, and the effects of reverberation. In this paper we review work on distant speech recognition, with an emphasis on approaches which combine multichannel signal processing with acoustic modelling, and investigate the use of hybrid neural network / hidden Markov model acoustic models for distant speech recognition of meetings recorded using microphone arrays. In particular we investigate the use of convolutional and fully-connected neural networks with different activation functions (sigmoid, rectified linear, and maxout). We performed experiments on the AMI and ICSI meeting corpora, with results indicating that neural network models are capable of significant improvements in accuracy compared with discriminatively trained Gaussian mixture models.

Predicting the Trend of Stock Market Index Using the Hybrid Neural Network Based on Multiple Time Scale Feature Learning

Abstract: In the stock market, predicting the trend of price series is one of the most widely investigated and challenging problems for investors and researchers. There are multiple time scale features in financial time series due to different durations of impact factors and traders’ trading behaviors. In this paper, we propose a novel end-to-end hybrid neural network, a model based on multiple time scale feature learning to predict the price trend of the stock market index. Firstly, the hybrid neural network extracts two types of features on different time scales through the first and second layers of the convolutional neural network (CNN), together with the raw daily price series, reflect relatively short-, medium- and long-term features in the price sequence. Secondly, considering time dependencies existing in the three kinds of features, the proposed hybrid neural network leverages three long short-term memory (LSTM) recurrent neural networks to capture such dependencies, respectively. Finally, fully connected layers are used to learn joint representations for predicting the price trend. The proposed hybrid neural network demonstrates its effectiveness by outperforming benchmark models on the real dataset.

Medical Image Classification Using a Light-Weighted Hybrid Neural Network Based on PCANet and DenseNet

Abstract: Medical image classification plays an important role in disease diagnosis since it can provide important reference information for doctors. The supervised convolutional neural networks (CNNs) such as DenseNet provide the versatile and effective method for medical image classification tasks, but they require large amounts of data with labels and involve complex and time-consuming training process. The unsupervised CNNs such as principal component analysis network (PCANet) need no labels for training but cannot provide desirable classification accuracy. To realize the accurate medical image classification in the case of a small training dataset, we have proposed a light-weighted hybrid neural network which consists of a modified PCANet cascaded with a simplified DenseNet. The modified PCANet has two stages, in which the network produces the effective feature maps at each stage by convoluting inputs with various learned kernels. The following simplified DenseNet with a small number of weights will take all feature maps produced by the PCANet as inputs and employ the dense shortcut connections to realize accurate medical image classification. To appreciate the performance of the proposed method, some experiments have been done on mammography and osteosarcoma histology images. Experimental results show that the proposed hybrid neural network is easy to train and it outperforms such popular CNN models as PCANet, ResNet and DenseNet in terms of classification accuracy, sensitivity and specificity.

Bio-Inspired Modeling of Cognitive Tasks

Abstract: Neural Networks and Quantum Neurology: Speculative Heuristic Towards the Architecture of Psychism.- Physical Basis of Quantum Computation and Cryptography.- Brain Organization and Computation.- Concepts and Models for the Future Generation of Emotional and Intelligent Systems.- Modeling Consciousness for Autonomous Robot Exploration.- An Insect-Inspired Active Vision Approach for Orientation Estimation with Panoramic Images.- Natural Interaction with a Robotic Head.- A Network of Interneurons Coupled by Electrical Synapses Behaves as a Coincidence Detector.- A Computational Structure for Generalized Visual Space-Time Chromatic Processing.- Physiological Laws of Sensory Visual System in Relation to Scaling Power Laws in Biological Neural Networks.- ANF Stochastic Low Rate Stimulation.- Functional Identification of Retinal Ganglion Cells Based on Neural Population Responses.- Towards a Neural-Networks Based Therapy for Limbs Spasticity.- A Bio-inspired Architecture for Cognitive Audio.- An Adaptable Multichannel Architecture for Cortical Stimulation.- Spiking Neural P Systems. Power and Efficiency.- Solving Subset Sum in Linear Time by Using Tissue P Systems with Cell Division.- On a P?un's Conjecture in Membrane Systems.- A Parallel DNA Algorithm Using a Microfluidic Device to Build Scheduling Grids.- P System Models of Bistable, Enzyme Driven Chemical Reaction Networks.- A Novel Improvement of Neural Network Classification Using Further Division of Partition Space.- Morphisms of ANN and the Computation of Least Fixed Points of Semantic Operators.- Predicting Human Immunodeficiency Virus (HIV) Drug Resistance Using Recurrent Neural Networks.- Error Weighting in Artificial Neural Networks Learning Interpreted as a Metaplasticity Model.- A First Approach to Birth Weight Prediction Using RBFNNs.- Filtering Documents with a Hybrid Neural Network Model.- A Single Layer Perceptron Approach to Selective Multi-task Learning.- Multi-task Neural Networks for Dealing with Missing Inputs.- Theoretical Study on the Capacity of Associative Memory with Multiple Reference Points.- Classification and Diagnosis of Heart Sounds and Murmurs Using Artificial Neural Networks.- Requirements for Machine Lifelong Learning.- Multitask Learning with Data Editing.- Efficient BP Algorithms for General Feedforward Neural Networks.- Coefficient Structure of Kernel Perceptrons and Support Vector Reduction.- The Max-Relevance and Min-Redundancy Greedy Bayesian Network Learning Algorithm.- On Affect and Self-adaptation: Potential Benefits of Valence-Controlled Action-Selection.- Detecting Anomalous Traffic Using Statistical Discriminator and Neural Decisional Motor.- A Learning Based Widrow-Hoff Delta Algorithm for Noise Reduction in Biomedical Signals.- Hopfield Neural Network and Boltzmann Machine Applied to Hardware Resource Distribution on Chips.- A New Rough Set Reduct Algorithm Based on Particle Swarm Optimization.- Use of Kohonen Maps as Feature Selector for Selective Attention Brain-Computer Interfaces.- Nature-Inspired Congestion Control: Using a Realistic Predator-Prey Model.- EDNA: Estimation of Dependency Networks Algorithm.- Grammar-Guided Neural Architecture Evolution.- Evolutionary Combining of Basis Function Neural Networks for Classification.- Non-linear Robust Identification: Application to a Thermal Process.- Gaining Insights into Laser Pulse Shaping by Evolution Strategies.- Simulated Evolution of the Adaptability of the Genetic Code Using Genetic Algorithms.- GCS with Real-Valued Input.- A Study on Genetic Algorithms for the DARP Problem.- Optimization of the Compression Parameters of a Phonocardiographic Telediagnosis System Using Genetic Algorithms.- An Integrated Resolution of Joint Production and Maintenance Scheduling Problem in Hybrid Flowshop.- Improving Cutting-Stock Plans with Multi-objective Genetic Algorithms.- Sensitivity Analysis for the Job Shop Problem with Uncertain Durations and Flexible Due Dates.- Comparative Study of Meta-heuristics for Solving Flow Shop Scheduling Problem Under Fuzziness.- Fusion of Neural Gas.- Decision Making Graphical Tool for Multiobjective Optimization Problems.- Electromagnetic Interference Reduction in Electronic Systems Cabinets by Means of Genetic Algorithms Design.- Evolutionary Tool for the Incremental Design of Controllers for Collective Behaviors.- A Possibilistic Approach for Mining Uncertain Temporal Relations from Diagnostic Evolution Databases.- Temporal Abstraction of States Through Fuzzy Temporal Constraint Networks.- Spieldose: An Interactive Genetic Software for Assisting to Music Composition Tasks.