Oscillation-Resisting in the Learning of Backpropagation Neural Networks

Deng, Xiaosong; Popović, D.; Schulz‐Ekloff, G.

doi:10.1016/s1474-6670(17)47206-5

Cited by 9 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2 Additionally, due to the possibility of spatially distributing the partitioned actuation system, the considered MPRs also exhibit a rather identical torque generation capability within their full range of motion (0    180°). Notice that this latter feature cannot be achieved by a standard 21 CSL mechanism actuated by a single continuously regulated force generator.…”

Section: Chapter 2 Five Ternary Mprs Mechanismsmentioning

confidence: 99%

Inverse Static Analysis of Massive Parallel Arrays of Three- State Actuators via Artificial Intelligence

Pasila

Vertechy

Berselli

et al. 2013

Romansy 19 – Robot Design, Dynamics and Control

View full text Add to dashboard Cite

Massive parallel robots (MPRs) driven by discrete actuators are force regulated robots that undergo continuous motions despite being commanded through a finite number of states only. Designing a real-time control of such systems requires fast and efficient methods for solving their inverse static analysis (ISA), which is a challenging problem and the subject of this thesis. In particular, five Artificial intelligence methods are proposed to investigate the on-line computation and the generalization error of ISA problem of a class of MPRs featuring three-state force actuators and one degree of revolute motion.

show abstract

Section: Chapter 2 Five Ternary Mprs Mechanismsmentioning

confidence: 99%

Inverse Static Analysis of Massive Parallel Arrays of Three- State Actuators via Artificial Intelligence

Pasila

Vertechy

Berselli

et al. 2013

Romansy 19 – Robot Design, Dynamics and Control

View full text Add to dashboard Cite

show abstract

“…Furthermore, Xiaosong et al [8] also proposed to add modified error index (MEI) term in order to improve training convergence. The corresponding gradient with MEI can now be defined by using a Jacobian matrix as: > @ …”

Section: If a Functionmentioning

confidence: 99%

Multivariate inputs for electrical load forecasting on hybrid neuro-fuzzy and fuzzy C-Means forecaster

Pasila

2008

2008 IEEE International Conference on Fuzzy Systems (IEEE World Congress on Computational Intelligence)

View full text Add to dashboard Cite

Multivariate inputs play important role in system with many dependent variables. By using some different inputs as input in neuro-fuzzy networks, complex nonlinear model can be modeled and also be forecasted with better results. This paper describes a neuro-fuzzy approach with additional fuzzy C-Means clustering method before the input entering the networks. Afterwards, the network can be used to efficiently forecast electrical load competition data using the Takagi-Sugeno (TS) type multi-input single-output (MISO) neuro-fuzzy network. The training algorithm is efficient in the sense that it can bring the performance index of the network, such as the sum squared error (SSE), down to the desired error goal much faster than the simple Levenberg-Marquardt algorithm (LMA).

show abstract

“…By substituting equation (21-24) into the (9-12), updated rules for free parameters can be written as To improve the training performance of feedforward NN, additional modified error index version should be added to the modified BPA with momentum, as proposed by Xiaosong et al [5]. This approach can be seen in equations (36-41).…”

Section: Bpa and Accelerated Bpamentioning

confidence: 99%

“…Furthermore, like in BPA, Xiaosong et al [5] also proposed to add modified error index (MEI) term in order to improve training convergence. Similar to equations (39-41), the corresponding gradient with MEI can now be defined by using a Jacobian matrix as: …”

mentioning

confidence: 99%

Comparison of BPA and LMA Methods for Takagi - Sugeno type MIMO Neuro-Fuzzy Network to Forecast Electrical Load Time Series

Pasila¹

2008

jte

View full text Add to dashboard Cite

This paper describes an accelerated Backpropagation algorithm (BPA) that can be used to train the Takagi-Sugeno (TS) type multi-input multi-output (MIMO) neuro-fuzzy network efficiently. Also other method such as accelerated LevenbergMarquardt algorithm (LMA) will be compared to BPA. The training algorithm is efficient in the sense that it can bring the performance index of the network, such as the sum squared error (SSE), Mean Squared Error (MSE), and also Root Mean Squared Error (RMSE), down to the desired error goal much faster than that the simple BPA or LMA. Finally, the above training algorithm is tested on neuro-fuzzy modeling and forecasting application of Electrical load time series.

show abstract

Oscillation-Resisting in the Learning of Backpropagation Neural Networks

Cited by 9 publications

References 4 publications

Inverse Static Analysis of Massive Parallel Arrays of Three- State Actuators via Artificial Intelligence

Inverse Static Analysis of Massive Parallel Arrays of Three- State Actuators via Artificial Intelligence

Multivariate inputs for electrical load forecasting on hybrid neuro-fuzzy and fuzzy C-Means forecaster

Comparison of BPA and LMA Methods for Takagi - Sugeno type MIMO Neuro-Fuzzy Network to Forecast Electrical Load Time Series

Contact Info

Product

Resources

About