Fast Retraining of Artificial Neural Networks

Nastac, Dumitru Iulian; Matei, Razvan

doi:10.1007/3-540-39205-x_77

Cited by 4 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next, the adaptivity of the result is performed (and improved), by applying the retraining technique [8], in a special way. This technique is a mechanism for extracting practical information directly from the weights of a reference ANN that had been already trained in a preliminary phase.…”

Section: Adaptive Retraining Proceduresmentioning

confidence: 99%

See 1 more Smart Citation

ANN Flexible Forecasting for the Adaptive Monitoring of a Multi-Tube Reactor

Nastac

Cristea

2007

2007 14th International Workshop on Systems, Signals and Image Processing and 6th EURASIP Conference Focused on Speech and Imag

View full text Add to dashboard Cite

The paper presents a flexible artificial neural network (ANN) model, in order to support modifications of a complex input-output function that describes the catalyst monitoring process of a multi-tube reactor. The goal is to obtain a good accuracy of the predicted data by using an optimal ANN architecture and well-suited delay vectors. The research targets the implementation of an adaptive system, which can be periodically retrained, in order to continuously learn the latest evolution of the catalyst process.

show abstract

Section: Adaptive Retraining Proceduresmentioning

confidence: 99%

“…An advantage of this technique is a significant decrease in the number of training cycles, compared to classical training methods [8].…”

Section: Adaptive Retraining Proceduresmentioning

confidence: 99%