scholarly journals A Novel Method for Training an Echo State Network with Feedback-Error Learning

2013 ◽  
Vol 2013 ◽  
pp. 1-9
Author(s):  
Rikke Amilde Løvlid
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Training Data ◽  
Echo State Network ◽  
Training Method ◽  
Computationally Efficient ◽  
Echo State Networks ◽  
Feedback Error Learning ◽  
Feedback Error ◽  
Error Learning

Echo state networks are a relatively new type of recurrent neural networks that have shown great potentials for solving non-linear, temporal problems. The basic idea is to transform the low dimensional temporal input into a higher dimensional state, and then train the output connection weights to make the system output the target information. Because only the output weights are altered, training is typically quick and computationally efficient compared to training of other recurrent neural networks. This paper investigates using an echo state network to learn the inverse kinematics model of a robot simulator with feedback-error-learning. In this scheme teacher forcing is not perfect, and joint constraints on the simulator makes the feedback error inaccurate. A novel training method which is less influenced by the noise in the training data is proposed and compared to the traditional ESN training method.

scholarly journals Computer Simulation Tests of Feedback Error Learning Controller with IDM and ISM for Functional Electrical Stimulation in Wrist Joint Control

2010 ◽  
Vol 2010 ◽  
pp. 1-11 ◽  
Author(s):  
Takashi Watanabe ◽  
Yoshihiro Sugi
Keyword(s):  
Computer Simulation ◽  
Electrical Stimulation ◽  
Functional Electrical Stimulation ◽  
Wrist Joint ◽  
Training Data ◽  
Joint Control ◽  
Feedback Error Learning ◽  
Feedback Error ◽  
Feedforward Controller ◽  
Error Learning

Feedforward controller would be useful for hybrid Functional Electrical Stimulation (FES) system using powered orthotic devices. In this paper, Feedback Error Learning (FEL) controller for FES (FEL-FES controller) was examined using an inverse statics model (ISM) with an inverse dynamics model (IDM) to realize a feedforward FES controller. For FES application, the ISM was tested in learning off line using training data obtained by PID control of very slow movements. Computer simulation tests in controlling wrist joint movements showed that the ISM performed properly in positioning task and that IDM learning was improved by using the ISM showing increase of output power ratio of the feedforward controller. The simple ISM learning method and the FEL-FES controller using the ISM would be useful in controlling the musculoskeletal system that has nonlinear characteristics to electrical stimulation and therefore is expected to be useful in applying to hybrid FES system using powered orthotic device.

scholarly journals Robot Manipulators Control with Guaranteed Stability Using Feedback Error Learning Neural Networks

1996 ◽  
Vol 8 (4) ◽  
pp. 383-391
Author(s):  
Ju-Jang Lee ◽  
◽  
Sung-Woo Kim ◽  
Kang-Bark Park
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Learning Rule ◽  
Neural Network Learning ◽  
Network Learning ◽  
The Neural Network ◽  
Control Schemes ◽  
Feedback Error Learning ◽  
Feedback Error ◽  
Error Learning

Among various neural network learning control schemes, feedback error learning(FEL)8),9) has been known that it has advantages over other schemes. However, such advantages are founded on the assumption that the systems is linearly parameterized and stable. Thus, FEL has difficulties in coping with uncertain and unstable systems. Furthermore, it is not clear how the learning rule of FEL is obtained in the minimization sense. Therefore, to overcome such problems, we propose neural network control schemes using FEL with guaranteed performance. The proposed strategy is to use multi-layer neural networks, to design a stabilityguaranteeing controller(SGC), and to derive a learning rule to obtain the tracking performance. Using multilayer neural networks we can fully utilize the learning capability no matter how the system is linearly parameterized or not. The SGC makes it possible for the neural network to learn without fear of instability. As a result, the more the neural network learning proceeds, the better the tracking performance becomes.

scholarly journals Applying RBF Neural Nets for Position Control of an Inter/Scara Robot

2009 ◽  
Vol 4 (2) ◽  
pp. 148
Author(s):  
Fernando Passold
Keyword(s):  
Neural Networks ◽  
Position Control ◽  
Sliding Mode ◽  
Neural Nets ◽  
Rbf Neural Networks ◽  
Feedback Error Learning ◽  
Feedback Error ◽  
On Line ◽  
Error Learning ◽  
Manipulator Robot

This paper describes experimental results applying artificial neural networks to perform the position control of a real scara manipulator robot. The general control strategy consists of a neural controller that operates in parallel with a conventional controller based on the feedback error learning architecture. The main advantage of this architecture is that it does not require any modification of the previous conventional controller algorithm. MLP and RBF neural networks trained on-line have been used, without requiring any previous knowledge about the system to be controlled. These approach has performed very successfully, with better results obtained with the RBF networks when compared to PID and sliding mode positional controllers.

scholarly journals Sample-level sound synthesis with recurrent neural networks and conceptors

2019 ◽  
Vol 5 ◽  
pp. e205 ◽  
Author(s):  
Chris Kiefer
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Synthesis Method ◽  
Network Models ◽  
Sound Synthesis ◽  
Boolean Logic ◽  
Training Data ◽  
Sound Design ◽  
Echo State Networks ◽  
Granular Synthesis

Conceptors are a recent development in the field of reservoir computing; they can be used to influence the dynamics of recurrent neural networks (RNNs), enabling generation of arbitrary patterns based on training data. Conceptors allow interpolation and extrapolation between patterns, and also provide a system of boolean logic for combining patterns together. Generation and manipulation of arbitrary patterns using conceptors has significant potential as a sound synthesis method for applications in computer music but has yet to be explored. Conceptors are untested with the generation of multi-timbre audio patterns, and little testing has been done on scalability to longer patterns required for audio. A novel method of sound synthesis based on conceptors is introduced. Conceptular Synthesis is based on granular synthesis; sets of conceptors are trained to recall varying patterns from a single RNN, then a runtime mechanism switches between them, generating short patterns which are recombined into a longer sound. The quality of sound resynthesis using this technique is experimentally evaluated. Conceptor models are shown to resynthesise audio with a comparable quality to a close equivalent technique using echo state networks with stored patterns and output feedback. Conceptor models are also shown to excel in their malleability and potential for creative sound manipulation, in comparison to echo state network models which tend to fail when the same manipulations are applied. Examples are given demonstrating creative sonic possibilities, by exploiting conceptor pattern morphing, boolean conceptor logic and manipulation of RNN dynamics. Limitations of conceptor models are revealed with regards to reproduction quality, and pragmatic limitations are also shown, where rises in computation and memory requirements preclude the use of these models for training with longer sound samples. The techniques presented here represent an initial exploration of the sound synthesis potential of conceptors, demonstrating possible creative applications in sound design; future possibilities and research questions are outlined.

Sign in / Sign up

Export Citation Format

Share Document