scholarly journals An Agent Program Capable of Applying Local Search Strategies in the State Space of Well Defined Problems

2018 ◽  
Author(s):  
Thayanne França ◽  
Raimundo J. C. F. Junior ◽  
Jherson H. A. Pereira ◽  
Francisca R. de V. Silveira ◽  
Lidio M. L. De Campos ◽  
...  
Keyword(s):  
Neural Network ◽  
Local Search ◽  
State Space ◽  
Search Strategies ◽  
The State ◽  
Systematic Search ◽  
Automatic Design ◽  
Agent System ◽  
Classical Models

Classical models of agents for solving well-defined problems are widely used in the literature but are limited to systematic search strategies in order to find the solutions. However, these strategies are not suited for all types of application. This work presents an adaption of classical models of agents for local search strategies. One agent system for neural network automatic design is used to show the feasibility of the proposal. The results are promising, since the model found satisfactory solutions for the proposed problems.

NEURAL NETWORK-BASED DIGITAL REDESIGN APPROACH FOR CONTROL OF UNKNOWN CONTINUOUS-TIME CHAOTIC SYSTEMS

2005 ◽  
Vol 15 (08) ◽  
pp. 2433-2455
Author(s):  
JOSE I. CANELON ◽  
LEANG S. SHIEH ◽  
SHU M. GUO ◽  
HEIDAR A. MALKI
Keyword(s):  
Neural Network ◽  
State Space ◽  
Continuous Time ◽  
Digital Control ◽  
Chaotic Systems ◽  
Linear Time ◽  
The State ◽  
Control Law ◽  
Analog Control ◽  
Digital Redesign

This paper presents a neural network-based digital redesign approach for digital control of continuous-time chaotic systems with unknown structures and parameters. Important features of the method are that: (i) it generalizes the existing optimal linearization approach for the class of state-space models which are nonlinear in the state but linear in the input, to models which are nonlinear in both the state and the input; (ii) it develops a neural network-based universal optimal linear state-space model for unknown chaotic systems; (iii) it develops an anti-digital redesign approach for indirectly estimating an analog control law from a fast-rate digital control law without utilizing the analog models. The estimated analog control law is then converted to a slow-rate digital control law via the prediction-based digital redesign method; (iv) it develops a linear time-varying piecewise-constant low-gain tracker which can be implemented using microprocessors. Illustrative examples are presented to demonstrate the effectiveness of the proposed methodology.

Building up Embodiment in Learning Agents Using A Gaussian Radial Basis Function Neural Network

2000 ◽  
Vol 12 (6) ◽  
pp. 656-663
Author(s):  
Hajime Murao ◽  
◽  
Shinzo Kitamura
Keyword(s):  
Neural Network ◽  
Radial Basis Function ◽  
State Space ◽  
Performance Improvement ◽  
Basis Function ◽  
The State ◽  
Learning Agents ◽  
Radial Basis ◽  
Space Construction ◽  
Hidden Layer

In this paper, we propose actor-critic learning with adaptive state space construction. The gaussian radial basis function neural network is employed for both the actor and the critic modules, where each hidden neuron covers a subspace of the sensor space and so the hidden layer corresponds to the state space. In the proposed algorithm, a robot starts without any states and a new state is generated incrementally by adding a new hidden neuron. One clear advantage of the proposed algorithm to others is the performance improvement by the minimal training after adding a new state, i.e. the adjustment of the connective strength between the new neuron and others is only required after adding a new hidden neuron. This provides an efficient method to construct the state space during the learning in the real world. Resulting state space represents aspects of the environment in which the robot works and the characteristic of the robot itself. In this sense, the obtained state space is said to represent the embodiment of the robot.

Modified ANN Inverse Compensating Method for Two-Dimensional Sensor

2013 ◽  
Vol 303-306 ◽  
pp. 266-269
Author(s):  
Yu Han Ding ◽  
Guo Hai Liu ◽  
Xian Zhong Dai
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
State Space ◽  
Dynamic Performance ◽  
The State ◽  
Two Dimensional ◽  
Modified Method ◽  
Artificial Neural ◽  
Space Equation

To improve the dynamic performance of the two-dimensional sensors, we presented a modified ANN (artificial neural network) inverse compensating method. The modified method is based on the state-space equation, which can fully describe the complex sensor and make the obtained inverse compensator more accurate, as well as decrease the derivative orders appeared in the inverse compensator. Simulation result verifies the modified compensator is more suitable to be used to compensate the complex two-dimensional sensor and the compensating result of the modified method is better that of the unmodified one.

On the State Space of the Binary Neural Network

1988 ◽  
Author(s):  
Moshe Kam ◽  
Roger Cheng ◽  
Allon Guez
Keyword(s):  
Neural Network ◽  
State Space ◽  
The State ◽  
Binary Neural Network

Research on State-Space Mapping Algorithm from the Vehicle Unsteady Constraint Test System to the Independent Vehicle System

2011 ◽  
Vol 130-134 ◽  
pp. 326-331 ◽  
Author(s):  
Guo Ye Wang ◽  
Juan Li Zhang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
State Space ◽  
Test System ◽  
Space Mapping ◽  
The State ◽  
Dynamics Simulation ◽  
Mapping Algorithm ◽  
Vehicle System ◽  
Artificial Neural

Project the vehicle unsteady constraint test system for testing vehicle ESP control performances safely and efficiently, set up the test system dynamics model. Based on the Matlab/Simulink establish the dynamics simulation system of the vehicle unsteady constraint test system for the Chery A3 car. Using the simulation model, we respectively simulate the stability control performances of the test system and the independent vehicle system on steady-state conditions of under steering and over steering. Research and verify the state-space mapping algorithm from the test system to the independent vehicle system using the artificial neural network. The study results indicate that the state-space mapping algorithm from the vehicle unsteady constraint test system to the independent vehicle system using the artificial neural network has ideal mapping performance, it will provide a theoretical basis and technical support for researching the vehicle ESP control performances based on the vehicle unsteady constraint test system.

CONTROL OF THE COMPLEXITY OF ASSOCIATIVE MEMORY DYNAMICS BY NEURONAL ADAPTATION

1993 ◽  
Vol 04 (02) ◽  
pp. 129-141 ◽  
Author(s):  
BO CARTLING
Keyword(s):  
Neural Network ◽  
State Space ◽  
Associative Memory ◽  
Action Potentials ◽  
The State ◽  
Degree Of Freedom ◽  
Neuronal Adaptation ◽  
Firing Rates ◽  
Associative Process ◽  
The Brain

An abstract neural network model of the Hopfield type is extended to incorporate neuronal adaptation by defining the state of a neuron in terms of two variables, activity and excitability. The model is formulated to represent the regulation of the firing rate of action potentials in a biological system via the neuron cell membrane afterhyperpolarization by the effect of intracellular calcium ion concentration on the conductance of calcium sensitive potassium channels. It is shown that the complexity, and thus the exploratory degree, of associative memory dynamics are controlled by neuronal adaptability. At low adaptability, the dynamics have fixed point attractors corresponding to direct memory retrieval. In a subsequent region of adaptability values, a simple limit cycle persists with frequency increasing with adaptability. The range of frequencies agrees with that observed for theta rhythms of activity in the brain. A higher degree of freedom of the associative process corresponding to more complex dynamics, either limit cycles of varying complexity and period or chaotic behaviour, results at higher adaptability. In the brain, the neuronal adaptability is regulated by neuromodulators which suppress adaptation and increase absolute firing rates of action potentials. An associative process can be started at low concentration of neuromodulators as an exploratory search of state space during which firing rates are low. As the concentration of neuromodulators increases, the state space search becomes simpler cyclic and more restricted, and firing rates increase. Eventually, a particular stored state is retrieved and its activity is high. This correspondence between the complexity of associative memory dynamics and the concentration of neuromodulators is consistent with the observation for Alzheimer's disease of selective degeneracy of neurons releasing the neuromodulator acetylcholine. In an artificial neural network, inclusion of adaptation among neuronal properties allows control of the degree of freedom of associative processes and thus extends the range of possible applications.

Accurate and Transferable Multitask Prediction of Chemical Properties with an Atoms-in-Molecule Neural Network

2018 ◽  
Author(s):  
Roman Zubatyuk ◽  
Justin S. Smith ◽  
Jerzy Leszczynski ◽  
Olexandr Isayev
Keyword(s):  
Neural Network ◽  
Molecular System ◽  
Computational Cost ◽  
Chemical Properties ◽  
The State ◽  
Molecular Properties ◽  
Training Data ◽  
Dft Methods ◽  
Benchmark Datasets ◽  
Quantum Phenomena

<p>Atomic and molecular properties could be evaluated from the fundamental Schrodinger’s equation and therefore represent different modalities of the same quantum phenomena. Here we present AIMNet, a modular and chemically inspired deep neural network potential. We used AIMNet with multitarget training to learn multiple modalities of the state of the atom in a molecular system. The resulting model shows on several benchmark datasets the state-of-the-art accuracy, comparable to the results of orders of magnitude more expensive DFT methods. It can simultaneously predict several atomic and molecular properties without an increase in computational cost. With AIMNet we show a new dimension of transferability: the ability to learn new targets utilizing multimodal information from previous training. The model can learn implicit solvation energy (like SMD) utilizing only a fraction of original training data, and archive MAD error of 1.1 kcal/mol compared to experimental solvation free energies in MNSol database.</p>

Sign in / Sign up

Export Citation Format

Share Document