AN EFFECTIVE NEURAL MODEL MECHANIZING HARD CAUSAL REASONING PROBLEMS WITH WTA and WTO NEURAL COMPUTATIONS

2004 ◽  
Vol 13 (03) ◽  
pp. 669-689 ◽  
Author(s):  
LOTFI BEN ROMDHANE ◽  
BECHIR AYEB
Keyword(s):  
Energy Function ◽  
Causal Reasoning ◽  
Gradient Descent ◽  
Neural Model ◽  
Neural Computation ◽  
Global Energy ◽  
Reasoning Process ◽  
Neural Computations ◽  
Simulation Results ◽  
Update Rules

In this work, we develop a neural model to solve causal reasoning problems (said also abduction) in the open, independent and incompatibility classes. We model the reasoning process by a single and global energy function using cooperative and competitive neural computation. The update rules of the distinct connections of the network are derived from its energy function using gradient descent techniques. Simulation results reveal a good performance of the model.

AN ARTIFICIAL NETWORK FOR REASONING IN THE CANCELLATION CLASS WITH APPLICATION TO THE DIAGNOSIS OF CELLS DIVISION

2005 ◽  
Vol 13 (03) ◽  
pp. 297-320
Author(s):  
LOTFI BEN ROMDHANE
Keyword(s):  
Causal Reasoning ◽  
Neural Model ◽  
Cognitive Agents ◽  
Rainy Weather ◽  
Simulation Results ◽  
Artificial Network

Causal reasoning is a hard task that cognitive agents perform reliably and quickly. A particular class of causal reasoning that raises several difficulties is the cancellation class. Cancellation occurs when a set of causes (hypotheses) cancel each other's explanation with respect to a given effect (observation). For example, a cloudy sky may suggest a rainy weather; whereas a shiny sky may suggest the absence of rain. In this work we extend a recent neural model to handle cancellation interactions. Simulation results are very satisfactory and should encourage research.

scholarly journals Evasion guidance for air-breathing hypersonic vehicles against unknown pursuer dynamics

2021 ◽  
Author(s):  
Tian Yan ◽  
Yuanli Cai ◽  
Bin Xu
Keyword(s):  
Parameter Estimation ◽  
Gradient Descent ◽  
Rapid Development ◽  
Energy Optimization ◽  
Hypersonic Vehicles ◽  
Air Breathing ◽  
Related Research ◽  
Practical Guidance ◽  
Simulation Results ◽  
Guidance Algorithm

AbstractThe rapid development of hypersonic vehicles has motivated the related research dramatically while the evasion of the hypersonic vehicles becomes one of the challenging issues. Different from the work based on the premise that the pursuers’ information is fully known, in this paper the evasion guidance for air-breathing hypersonic vehicles (AHVs) against unknown pursuer dynamics is studied. The gradient descent is employed for parameter estimation of the unknown dynamics of the pursuer. The energy-optimized evasion guidance algorithm is further developed by taking the acceleration constraint and energy optimization into consideration. Under the proposed algorithm, the system can deal with the unknown pursuer dynamics effectively and provide more practical guidance for the evasion process. The simulation results show that the proposed method can enable the AHV to achieve successful evasion.

The TP Chromatic Aberration Estimation by Using Neural Networks

2011 ◽  
Vol 121-126 ◽  
pp. 4239-4243 ◽  
Author(s):  
Du Jou Huang ◽  
Yu Ju Chen ◽  
Huang Chu Huang ◽  
Yu An Lin ◽  
Rey Chue Hwang
Keyword(s):  
Neural Networks ◽  
Learning Algorithm ◽  
Back Propagation ◽  
Physical Property ◽  
Chromatic Aberration ◽  
Neural Model ◽  
Artificial Intelligent ◽  
Error Back Propagation ◽  
The Neural Networks ◽  
Simulation Results

The chromatic aberration estimations of touch panel (TP) film by using neural networks are presented in this paper. The neural networks with error back-propagation (BP) learning algorithm were used to catch the complex relationship between the chromatic aberration, i.e., L.A.B. values, and the relative parameters of TP decoration film. An artificial intelligent (AI) estimator based on neural model for the estimation of physical property of TP film is expected to be developed. From the simulation results shown, the estimations of chromatic aberration of TP film are very accurate. In other words, such an AI estimator is quite promising and potential in commercial using.

DOES ABNORMAL SPINAL RECIPROCAL INHIBITION LEAD TO CO-CONTRACTION OF ANTAGONIST MOTOR UNITS? A MODELING STUDY

2007 ◽  
Vol 17 (04) ◽  
pp. 319-327 ◽  
Author(s):  
VASSILIS CUTSURIDIS
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Motor Neurons ◽  
Motor Units ◽  
Neural Model ◽  
Reciprocal Inhibition ◽  
Dopamine Depletion ◽  
Cortical Cells ◽  
Simulation Results ◽  
Modeling Study

It is suggested that co-contraction of antagonist motor units perhaps due to abnormal disynaptic I a reciprocal inhibition is responsible for Parkinsonian rigidity. A neural model of Parkinson's disease bradykinesia is extended to incorporate the effects of spindle feedback on key cortical cells and examine the effects of dopamine depletion on spinal activities. Simulation results show that although reciprocal inhibition is reduced in DA depleted case, it doesn't lead to co-contraction of antagonist motor neurons. Implications to Parkinsonian rigidity are discussed.

scholarly journals Klasifikasi Multi Output pada Harga Smartphone Menggunakan Learning Vector Quantization (LVQ) dan Backpropagation (BP)

2021 ◽  
Vol 6 (2) ◽  
pp. 14-19
Author(s):  
Dinita Rahmalia ◽  
Mohammad Syaiful Pradana ◽  
Teguh Herlambang
Keyword(s):  
Vector Quantization ◽  
Error Rate ◽  
Gradient Descent ◽  
Euclidean Distance ◽  
Learning Vector Quantization ◽  
Training Data ◽  
Price Range ◽  
Testing Data ◽  
Internal Storage ◽  
Simulation Results

There are many smartphones with various price sold in market. The price of smartphone is affected by some components such as weight, internal storage, memory (RAM), rear camera, front camera and brands. There are two methods for classifying price class of smartphone in market such as Learning Vector Quantization (LVQ) and Backpropagation (BP). From classifying price class of smartphone in market using LVQ and BP, there are the differences on the both of them. LVQ classifies price range of smartphone by euclidean distance of weight and data on its iteration. BP classifies price range of smartphone by gradient descent of target and output on its iteration. In multi output classification, one object may have multi output. Based on simulation results, BP gives the better accuracy and error rate in training data and testing data than LVQ.  

scholarly journals Identifying Functional Bases for Multidimensional Neural Computations

2013 ◽  
Vol 25 (7) ◽  
pp. 1870-1890 ◽  
Author(s):  
Joel Kaardal ◽  
Jeffrey D. Fitzgerald ◽  
Michael J. Berry ◽  
Tatyana O. Sharpee
Keyword(s):  
Dimensionality Reduction ◽  
Predictive Models ◽  
Ganglion Cells ◽  
Nonlinear Function ◽  
Neural Circuitry ◽  
Neural Computation ◽  
Functional Basis ◽  
Neural Computations ◽  
Reduction Methods ◽  
Functional Features

Current dimensionality-reduction methods can identify relevant subspaces for neural computations but do not favor one basis over the other within the relevant subspace. Finding the appropriate basis can simplify the description of the nonlinear computation with respect to the relevant variables, making it easier to elucidate the underlying neural computation and make hypotheses about the neural circuitry, giving rise to the observed responses. Part of the problem is that although some of the dimensionality reduction methods can identify many of the relevant dimensions, it is usually difficult to map out or interpret the nonlinear transformation with respect to more than a few relevant dimensions simultaneously without some simplifying assumptions. While recent approaches make it possible to create predictive models based on many relevant dimensions simultaneously, there still remains the need to relate such predictive models to the mechanistic descriptions of the operation of underlying neural circuitry. Here we demonstrate that transforming to a basis within the relevant subspace where the neural computation is best described by a given nonlinear function often makes it easier to interpret the computation and describe it with a small number of parameters. We refer to the corresponding basis as the functional basis, and illustrate the utility of such transformation in the context of logical OR and logical AND functions. We show that although dimensionality-reduction methods such as spike-triggered covariance are able to find a relevant subspace, they often produce dimensions that are difficult to interpret and do not correspond to a functional basis. The functional features can be found using a maximum likelihood approach. The results are illustrated using simulated neurons and recordings from retinal ganglion cells. The resulting features are uniquely defined and nonorthogonal, and they make it easier to relate computational and mechanistic models to each other.

The Coordinated Immersion and Variance Control of Power Systems With Excitation and Steam-Valve

2017 ◽  
Vol 140 (4) ◽  
Author(s):  
Shengtao Li ◽  
Xiaomei Liu ◽  
Xiaoping Liu
Keyword(s):  
Power Systems ◽  
Energy Function ◽  
Transient Stability ◽  
Lyapunov Method ◽  
Control Performance ◽  
Immersion And Invariance ◽  
Angle Stability ◽  
Simulation Results ◽  
Lyapunov Energy Function ◽  
Large Disturbance

Transient stability is the key problem for reliable and secure planning under the new deregulated market conditions. By using immersion and invariance (I&I) method, a nonlinear coordinated generator excitation and steam-valve controller is designed to improve transient stability of power systems. The proposed coordinated I&I controller can assure power angle stability, voltage, and frequency regulations, when a large disturbance occurs on the transmission line or a small perturbation to mechanical power. Compared with the Lyapunov method, the proposed method does not need to construct a Lyapunov energy function. Some numerical simulations are used to validate the proposed controller. Simulation results show that the nonlinear coordinated I&I controller has better control performance than the existing coordinated passivation controller (CPC).

scholarly journals A Generalized Linear Integrate-and-Fire Neural Model Produces Diverse Spiking Behaviors

2009 ◽  
Vol 21 (3) ◽  
pp. 704-718 ◽  
Author(s):  
Ştefan Mihalaş ◽  
Ernst Niebur
Keyword(s):  
Differential Equations ◽  
Biological Significance ◽  
Polynomial Equation ◽  
Neural Model ◽  
Fire Model ◽  
Variable Threshold ◽  
Integrate And Fire ◽  
Linear Differential ◽  
Update Rules ◽  
Parameter Values

For simulations of neural networks, there is a trade-off between the size of the network that can be simulated and the complexity of the model used for individual neurons. In this study, we describe a generalization of the leaky integrate-and-fire model that produces a wide variety of spiking behaviors while still being analytically solvable between firings. For different parameter values, the model produces spiking or bursting, tonic, phasic or adapting responses, depolarizing or hyperpolarizing after potentials and so forth. The model consists of a diagonalizable set of linear differential equations describing the time evolution of membrane potential, a variable threshold, and an arbitrary number of firing-induced currents. Each of these variables is modified by an update rule when the potential reaches threshold. The variables used are intuitive and have biological significance. The model's rich behavior does not come from the differential equations, which are linear, but rather from complex update rules. This single-neuron model can be implemented using algorithms similar to the standard integrate-and-fire model. It is a natural match with event-driven algorithms for which the firing times are obtained as a solution of a polynomial equation.

Sign in / Sign up

Export Citation Format

Share Document