scholarly journals Neuronic Convolution Model_Li-Yun Fu

2020 ◽  
Author(s):  
Li-Yun Fu
Keyword(s):  
Neuron Model ◽  
Back Propagation ◽  
Kernel Functions ◽  
Spatiotemporal Pattern ◽  
Information Representation ◽  
Back Propagation Algorithm ◽  
Multilayer Network ◽  
Artificial Neuron ◽  
Spatiotemporal Information ◽  
Pattern Processing

How to represent spatiotemporal information in an artificial neuron model has been a problem of longstanding interest in artificial intelligence. After a brief review of recent advances, Caianiello’s neuronic convolutional model is extended in this paper for spatiotemporal information representation. The kernel functions that correspond to the convolutional neuron’s receptive field profile can be described by neural wavelets. The convolutional neuron-based multilayer network and its back propagation algorithm are developed to perform spatiotemporal pattern processing. The results provide a natural framework for the discussion of spatiotemporal information representation in an artificial neural network

scholarly journals Neuronic Convolution Model_Li-Yun Fu

2020 ◽  
Author(s):  
Li-Yun Fu
Keyword(s):  
Neuron Model ◽  
Back Propagation ◽  
Kernel Functions ◽  
Spatiotemporal Pattern ◽  
Information Representation ◽  
Back Propagation Algorithm ◽  
Multilayer Network ◽  
Artificial Neuron ◽  
Spatiotemporal Information ◽  
Pattern Processing

How to represent spatiotemporal information in an artificial neuron model has been a problem of longstanding interest in artificial intelligence. After a brief review of recent advances, Caianiello’s neuronic convolutional model is extended in this paper for spatiotemporal information representation. The kernel functions that correspond to the convolutional neuron’s receptive field profile can be described by neural wavelets. The convolutional neuron-based multilayer network and its back propagation algorithm are developed to perform spatiotemporal pattern processing. The results provide a natural framework for the discussion of spatiotemporal information representation in an artificial neural network

CONNECTIONIST MODEL BINARIZATION

1991 ◽  
Vol 05 (04) ◽  
pp. 629-644 ◽  
Author(s):  
NOBORU BABAGUCHI ◽  
KOJI YAMADA ◽  
KOICHI KISE ◽  
YOSHIKAZU TEZUKA
Keyword(s):  
Back Propagation ◽  
Connectionist Model ◽  
Gray Level ◽  
Threshold Selection ◽  
Back Propagation Algorithm ◽  
Image Binarization ◽  
Multilayer Network ◽  
Binarization Method ◽  
Gray Level Histogram ◽  
Binarized Image

Image binarization is a task to convert gray-level images into bi-level ones. Its underlying notion can be simply thought of as threshold selection. However, the result of binarization will cause significant influence on the process of image recognition or understanding. In this paper we discuss a new binarization method, named CMB (connectionist model binarization), which uses the connectionist model. In the method a gray-level histogram is input to a multilayer network trained with the back-propagation algorithm to obtain a threshold which gives a visually suitable binarized image. From the experimental results, it was verified that CMB is an effective binarization method in comparison with other methods.

RECOGNITION OF ACTIONS IN DAILY LIFE AND ITS PERFORMANCE ADJUSTMENT BASED ON SUPPORT VECTOR LEARNING

2004 ◽  
Vol 01 (04) ◽  
pp. 565-583 ◽  
Author(s):  
TAKETOSHI MORI ◽  
MASAMICHI SHIMOSAKA ◽  
TATSUYA HARADA ◽  
TOMOMASA SATO
Keyword(s):  
Intelligent Systems ◽  
Daily Life ◽  
Back Propagation ◽  
Kernel Functions ◽  
Support Vector ◽  
Human Knowledge ◽  
Back Propagation Algorithm ◽  
Recognition Method ◽  
Learning Capability ◽  
Robust Learning

This paper presents a recognition method for human actions in daily life. The system deals with actions related to regular human activity such as walking or lying down. The main features of the proposed method are: (i) simultaneous recognition, (ii) expressing lack of clarity in human recognition, (iii) defining similarities between two motions by utilizing kernel functions derived from expressions of actions based on human knowledge, (iv) robust learning capability based on support vector machine. Comparison with neural networks optimized by a back propagation algorithm and decision trees generated by C4.5 proves that the accuracy of recognition in the proposed method is superior to others. Recognizing actions in daily life robustly is expected to ensure smooth communication between humans and robots and to enhance support functionality in intelligent systems.

Construction of a deep sparse filtering network for rotating machinery fault diagnosis

2021 ◽  
pp. 095440702110148
Author(s):  
Chun Cheng ◽  
Wei Zou ◽  
Weiping Wang ◽  
Michael Pecht
Keyword(s):  
Fault Diagnosis ◽  
Back Propagation ◽  
Feature Learning ◽  
Back Propagation Neural Network ◽  
Rotating Machinery ◽  
Fine Tuning ◽  
Local Optimum ◽  
Back Propagation Algorithm ◽  
Intelligent Fault Diagnosis ◽  
Sparse Filtering

Deep neural networks (DNNs) have shown potential in intelligent fault diagnosis of rotating machinery. However, traditional DNNs such as the back-propagation neural network are highly sensitive to the initial weights and easily fall into the local optimum, which restricts the feature learning capability and diagnostic performance. To overcome the above problems, a deep sparse filtering network (DSFN) constructed by stacked sparse filtering is developed in this paper and applied to fault diagnosis. The developed DSFN is pre-trained by sparse filtering in an unsupervised way. The back-propagation algorithm is employed to optimize the DSFN after pre-training. Then, the DSFN-based intelligent fault diagnosis method is validated using two experiments. The results show that pre-training with sparse filtering and fine-tuning can help the DSFN search for the optimal network parameters, and the DSFN can learn discriminative features adaptively from rotating machinery datasets. Compared with classical methods, the developed diagnostic method can diagnose rotating machinery faults with higher accuracy using fewer training samples.

scholarly journals Two-Stage Water Jet Landing Point Prediction Model for Intelligent Water Shooting Robot

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2704
Author(s):  
Yunhan Lin ◽  
Wenlong Ji ◽  
Haowei He ◽  
Yaojie Chen
Keyword(s):  
Pitch Angle ◽  
Back Propagation ◽  
Water Jet ◽  
The State ◽  
Model Parameters ◽  
Propagation Time ◽  
Back Propagation Algorithm ◽  
Angle Error ◽  
Landing Point ◽  
Propagation Algorithm

In this paper, an intelligent water shooting robot system for situations of carrier shake and target movement is designed, which uses a 2 DOF (degree of freedom) robot as an actuator, a photoelectric camera to detect and track the desired target, and a gyroscope to keep the robot’s body stable when it is mounted on the motion carriers. Particularly, for the accurate shooting of the designed system, an online tuning model of the water jet landing point based on the back-propagation algorithm was proposed. The model has two stages. In the first stage, the polyfit function of Matlab is used to fit a model that satisfies the law of jet motion in ideal conditions without interference. In the second stage, the model uses the back-propagation algorithm to update the parameters online according to the visual feedback of the landing point position. The model established by this method can dynamically eliminate the interference of external factors and realize precise on-target shooting. The simulation results show that the model can dynamically adjust the parameters according to the state relationship between the landing point and the desired target, which keeps the predicted pitch angle error within 0.1°. In the test on the actual platform, when the landing point is 0.5 m away from the position of the desired target, the model only needs 0.3 s to adjust the water jet to hit the target. Compared to the state-of-the-art method, GA-BP (genetic algorithm-back-propagation), the proposed method’s predicted pitch angle error is within 0.1 degree with 1/4 model parameters, while costing 1/7 forward propagation time and 1/200 back-propagation calculation time.

scholarly journals Deep neural networks using a single neuron: folded-in-time architecture using feedback-modulated delay loops

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Florian Stelzer ◽  
André Röhm ◽  
Raul Vicente ◽  
Ingo Fischer ◽  
Serhiy Yanchuk
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Network ◽  
Single Neuron ◽  
Deep Neural Networks ◽  
Back Propagation ◽  
Local Network ◽  
Multiple Time ◽  
Learning Tools ◽  
Back Propagation Algorithm

AbstractDeep neural networks are among the most widely applied machine learning tools showing outstanding performance in a broad range of tasks. We present a method for folding a deep neural network of arbitrary size into a single neuron with multiple time-delayed feedback loops. This single-neuron deep neural network comprises only a single nonlinearity and appropriately adjusted modulations of the feedback signals. The network states emerge in time as a temporal unfolding of the neuron’s dynamics. By adjusting the feedback-modulation within the loops, we adapt the network’s connection weights. These connection weights are determined via a back-propagation algorithm, where both the delay-induced and local network connections must be taken into account. Our approach can fully represent standard Deep Neural Networks (DNN), encompasses sparse DNNs, and extends the DNN concept toward dynamical systems implementations. The new method, which we call Folded-in-time DNN (Fit-DNN), exhibits promising performance in a set of benchmark tasks.

scholarly journals Using Artificial Neural Networks in Predicting the Level of Stress among Military Conscripts

Mathematics ◽  
2021 ◽  
Vol 9 (6) ◽  
pp. 626
Author(s):  
Svajone Bekesiene ◽  
Rasa Smaliukiene ◽  
Ramute Vaicaitiene
Keyword(s):  
Neural Network ◽  
Transfer Functions ◽  
Back Propagation ◽  
Armed Forces ◽  
Activation Function ◽  
Optimal Number ◽  
Ann Model ◽  
Back Propagation Algorithm ◽  
Classification Rate ◽  
Artificial Neural

The present study aims to elucidate the main variables that increase the level of stress at the beginning of military conscription service using an artificial neural network (ANN)-based prediction model. Random sample data were obtained from one battalion of the Lithuanian Armed Forces, and a survey was conducted to generate data for the training and testing of the ANN models. Using nonlinearity in stress research, numerous ANN structures were constructed and verified to limit the optimal number of neurons, hidden layers, and transfer functions. The highest accuracy was obtained by the multilayer perceptron neural network (MLPNN) with a 6-2-2 partition. A standardized rescaling method was used for covariates. For the activation function, the hyperbolic tangent was used with 20 units in one hidden layer as well as the back-propagation algorithm. The best ANN model was determined as the model that showed the smallest cross-entropy error, the correct classification rate, and the area under the ROC curve. These findings show, with high precision, that cohesion in a team and adaptation to military routines are two critical elements that have the greatest impact on the stress level of conscripts.

COMPUTING AN ADAPTIVE MESH IN FLUID PROBLEMS USING NEURAL NETWORK AND GENETIC ALGORITHM WITH ADAPTIVE RELAXATION

2008 ◽  
Vol 17 (06) ◽  
pp. 1089-1108 ◽  
Author(s):  
NAMEER N. EL. EMAM ◽  
RASHEED ABDUL SHAHEED
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Numerical Experiments ◽  
Back Propagation ◽  
Adaptive Mesh ◽  
Learning System ◽  
Back Propagation Algorithm ◽  
Adaptive Smoothing ◽  
Different Types ◽  
Optimal Values

A method based on neural network with Back-Propagation Algorithm (BPA) and Adaptive Smoothing Errors (ASE), and a Genetic Algorithm (GA) employing a new concept named Adaptive Relaxation (GAAR) is presented in this paper to construct learning system that can find an Adaptive Mesh points (AM) in fluid problems. AM based on reallocation scheme is implemented on different types of two steps channels by using a three layer neural network with GA. Results of numerical experiments using Finite Element Method (FEM) are discussed. Such discussion is intended to validate the process and to demonstrate the performance of the proposed learning system on three types of two steps channels. It appears that training is fast enough and accurate due to the optimal values of weights by using a few numbers of patterns. Results confirm that the presented neural network with the proposed GA consistently finds better solutions than the conventional neural network.

Sign in / Sign up

Export Citation Format

Share Document