Nonlinear Control of Dynamic Systems Using Single Multiplicative Neuron Models

2012 ◽  
Author(s):  
Jonathan G. Turner ◽  
Biswanath Samanta
Keyword(s):  
Nonlinear Control ◽  
Dynamic Systems ◽  
Optimization Technique ◽  
Real Life ◽  
Population Based ◽  
Motor Speed ◽  
Neuron Models ◽  
On Line ◽  
On Line Learning ◽  
Better Than

The paper presents an approach to nonlinear control of dynamic systems using artificial neural networks (ANN). A novel form of ANN, namely, single multiplicative neuron (SMN) model is proposed in place of more traditional multi-layer perceptron (MLP). SMN derives its inspiration from the single neuron computation model in neuroscience. SMN model is trained off-line, to estimate the network weights and biases, using a population based stochastic optimization technique, namely, particle swarm optimization (PSO). Both off-line training and on-line learning of SMN have been considered. The development of the control algorithm is illustrated through the hardware-in-the-loop (HIL) implementation of DC motor speed control in LabVIEW environment. The controller based on SMN performs better than MLP. The simple structure and faster computation of SMN have the potential to make it a preferred candidate for implementation of real-life complex control systems.

Nonlinear Control of a Magnetic Levitation System Using Single Multiplicative Neuron Models

2013 ◽  
Author(s):  
Daniel L. Hall ◽  
Biswanath Samanta
Keyword(s):  
Nonlinear Control ◽  
Feedback Linearization ◽  
Magnetic Levitation ◽  
Optimization Technique ◽  
Real Life ◽  
Population Based ◽  
Neuron Models ◽  
Levitation System ◽  
Magnetic Levitation System ◽  
The One

The paper presents an approach to nonlinear control of a magnetic levitation system using artificial neural networks (ANN). A novel form of ANN, namely, single multiplicative neuron (SMN) model is proposed in place of more traditional multi-layer perceptron (MLP). SMN derives its inspiration from the single neuron computation model in neuroscience. SMN model is trained off-line, to estimate the network weights and biases, using a population based stochastic optimization technique, namely, particle swarm optimization (PSO). Both off-line training and on-line learning of SMN have been considered. The ANN based techniques have been compared with a feedback linearization approach. The development of the control algorithms is illustrated through the hardware-in-the-loop (HIL) implementation of magnetic levitation in LabVIEW environment. The controllers based on ANN performed quite well and better than the one based on feedback linearization. However, the SMN structure was much simpler than the MLP for similar performance. The simple structure and faster computation of SMN have the potential to make it a preferred candidate for implementation of real-life complex magnetic levitation systems.

Particle Swarm Optimization from Theory to Applications

2018 ◽  
Vol 5 (2) ◽  
pp. 1-24 ◽  
Author(s):  
M.A. El-Shorbagy ◽  
Aboul Ella Hassanien
Keyword(s):  
Particle Swarm Optimization ◽  
Optimization Problems ◽  
Optimization Technique ◽  
Real Life ◽  
Particle Swarm ◽  
Population Based ◽  
Constrained Optimization Problems ◽  
Swarm Optimization ◽  
Combinatorial Optimization Problems ◽  
Unconstrained Optimization Problems

Particle swarm optimization (PSO) is considered one of the most important methods in swarm intelligence. PSO is related to the study of swarms; where it is a simulation of bird flocks. It can be used to solve a wide variety of optimization problems such as unconstrained optimization problems, constrained optimization problems, nonlinear programming, multi-objective optimization, stochastic programming and combinatorial optimization problems. PSO has been presented in the literature and applied successfully in real life applications. In this paper, a comprehensive review of PSO as a well-known population-based optimization technique. The review starts by a brief introduction to the behavior of the PSO, then basic concepts and development of PSO are discussed, it's followed by the discussion of PSO inertia weight and constriction factor as well as issues related to parameter setting, selection and tuning, dynamic environments, and hybridization. Also, we introduced the other representation, convergence properties and the applications of PSO. Finally, conclusions and discussion are presented. Limitations to be addressed and the directions of research in the future are identified, and an extensive bibliography is also included.

scholarly journals Understanding measure-driven algorithms solving irreversibly ill-conditioned problems

2021 ◽  
Author(s):  
Jakub Sawicki ◽  
Marcin Łoś ◽  
Maciej Smołka ◽  
Robert Schaefer
Keyword(s):  
Global Optimization ◽  
Markov Chain ◽  
Dynamic Systems ◽  
Positive Measure ◽  
Numerical Solutions ◽  
Optimization Problems ◽  
Real Life ◽  
Population Based ◽  
Ergodic Markov Chain ◽  
Markov Chain Models

AbstractThe paper helps to understand the essence of stochastic population-based searches that solve ill-conditioned global optimization problems. This condition manifests itself by presence of lowlands, i.e., connected subsets of minimizers of positive measure, and inability to regularize the problem. We show a convenient way to analyze such search strategies as dynamic systems that transform the sampling measure. We can draw informative conclusions for a class of strategies with a focusing heuristic. For this class we can evaluate the amount of information about the problem that can be gathered and suggest ways to verify stopping conditions. Next, we show the Hierarchic Memetic Strategy coupled with Multi-Winner Evolutionary Algorithm (HMS/MWEA) that follow the ideas from the first part of the paper. We introduce a complex, ergodic Markov chain of their dynamics and prove an asymptotic guarantee of success. Finally, we present numerical solutions to ill-conditioned problems: two benchmarks and a real-life engineering one, which show the strategy in action. The paper recalls and synthesizes some results already published by authors, drawing new qualitative conclusions. The totally new parts are Markov chain models of the HMS structure of demes and of the MWEA component, as well as the theorem of their ergodicity.

scholarly journals BrainFreeze: Expanding the Capabilities of Neuromorphic Systems Using Mixed-Signal Superconducting Electronics

2021 ◽  
Vol 15 ◽  
Author(s):  
Paul Tschirhart ◽  
Ken Segall
Keyword(s):  
Computational Neuroscience ◽  
Large Scale ◽  
Learning Support ◽  
Neuron Models ◽  
Neuromorphic Systems ◽  
On Line ◽  
Superconducting Electronics ◽  
Near Term ◽  
On Line Learning ◽  
New Generation

Superconducting electronics (SCE) is uniquely suited to implement neuromorphic systems. As a result, SCE has the potential to enable a new generation of neuromorphic architectures that can simultaneously provide scalability, programmability, biological fidelity, on-line learning support, efficiency and speed. Supporting all of these capabilities simultaneously has thus far proven to be difficult using existing semiconductor technologies. However, as the fields of computational neuroscience and artificial intelligence (AI) continue to advance, the need for architectures that can provide combinations of these capabilities will grow. In this paper, we will explain how superconducting electronics could be used to address this need by combining analog and digital SCE circuits to build large scale neuromorphic systems. In particular, we will show through detailed analysis that the available SCE technology is suitable for near term neuromorphic demonstrations. Furthermore, this analysis will establish that neuromorphic architectures built using SCE will have the potential to be significantly faster and more efficient than current approaches, all while supporting capabilities such as biologically suggestive neuron models and on-line learning. In the future, SCE-based neuromorphic systems could serve as experimental platforms supporting investigations that are not feasible with current approaches. Ultimately, these systems and the experiments that they support would enable the advancement of neuroscience and the development of more sophisticated AI.

Nonlinear control of UAVs using multi-layer perceptrons with off-line and on-line learning

2014 ◽  
Author(s):  
Subodh Bhandari ◽  
Amar Raheja ◽  
Daisy Tang ◽  
Kevin Ortega ◽  
Ohanes Dadian ◽  
...  
Keyword(s):  
Nonlinear Control ◽  
On Line ◽  
On Line Learning

Patterns of Implicit Learning Below the Level of Conscious Knowledge

2010 ◽  
Vol 24 (2) ◽  
pp. 91-101 ◽  
Author(s):  
Juliana Yordanova ◽  
Rolf Verleger ◽  
Ullrich Wagner ◽  
Vasil Kolev
Keyword(s):  
Implicit Learning ◽  
Explicit Knowledge ◽  
Implicit Knowledge ◽  
Knowledge Generation ◽  
Sleep Stages ◽  
Implicit Processing ◽  
Implicit Processes ◽  
Late Night ◽  
On Line ◽  
On Line Learning

The objective of the present study was to evaluate patterns of implicit processing in a task where the acquisition of explicit and implicit knowledge occurs simultaneously. The number reduction task (NRT) was used as having two levels of organization, overt and covert, where the covert level of processing is associated with implicit associative and implicit procedural learning. One aim was to compare these two types of implicit processes in the NRT when sleep was or was not introduced between initial formation of task representations and subsequent NRT processing. To assess the effects of different sleep stages, two sleep groups (early- and late-night groups) were used where initial training of the task was separated from subsequent retest by 3 h full of predominantly slow wave sleep (SWS) or rapid eye movement (REM) sleep. In two no-sleep groups, no interval was introduced between initial and subsequent NRT performance. A second aim was to evaluate the interaction between procedural and associative implicit learning in the NRT. Implicit associative learning was measured by the difference between the speed of responses that could or could not be predicted by the covert abstract regularity of the task. Implicit procedural on-line learning was measured by the practice-based increased speed of performance with time on task. Major results indicated that late-night sleep produced a substantial facilitation of implicit associations without modifying individual ability for explicit knowledge generation or for procedural on-line learning. This was evidenced by the higher rate of subjects who gained implicit knowledge of abstract task structure in the late-night group relative to the early-night and no-sleep groups. Independently of sleep, gain of implicit associative knowledge was accompanied by a relative slowing of responses to unpredictable items suggesting reciprocal interactions between associative and motor procedural processes within the implicit system. These observations provide evidence for the separability and interactions of different patterns of processing within implicit memory.

Sign in / Sign up

Export Citation Format

Share Document