Precision requirements for single-layer feedforward neural networks

Annema, Anne-Johan; Hoen, Klaas; Wallinga, Hans

doi:10.1109/icmnn.1994.593243

Cited by 18 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was shown in [5] that instead of noise during training, offsets on weight adaptations significantly degrade the learning capabilities of feed-forward neural networks; a short discussion of the results in [5] is presented furtheron in this article. In analog hardware, the offsets on weight adaptations are caused by offsets in any part of the weight adaptation circuitry.…”

Section: Introductionmentioning

confidence: 95%

“…A worst-case estimation on the maximum tolerable parasitic constant weight adaptation, i.e. the maximum t~lerable offset on the weight adaptation, is given in [5] for single neurons that use the backpropagation rule [1]. This analysis first estimates the steepness of the (local or global) minimum to be reached during training, and then estimates the maximum offset on the weight adaptations in order be able to arrive close to this (local or global) minimum.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analog weight adaptation hardware

Annema

Wallinga

1995

Neural Process Lett

Self Cite

View full text Add to dashboard Cite

Abstract. The demands on offsets in analog weight adaptation circuitry are very high for onchip learning feed-forward neural networks using a back-propagation type of learning rule. Exceeding of the specifications for weight adaptation offsets prevents the weights from converging to their optimum, which leads to a significantly degraded learning behavior. This letter presents a circuit, including a tuning system, that minimizes weight adaptation offsets and that can be used to implement analog on-chip back-propagation learning feed-forward neural networks.

show abstract

Section: Introductionmentioning

confidence: 95%

Section: Introductionmentioning

confidence: 99%

Analog weight adaptation hardware

Annema

Wallinga

1995

Neural Process Lett

Self Cite

View full text Add to dashboard Cite

show abstract

“…The extreme learning machine method proposed by Huang et al [16,17] uses the single layer feed forward neural network (SLFN) architecture [18]. It randomly chooses the input weights and analytically determines the output weights of the SLFN.…”

Section: Extreme Learning Machine Methodsmentioning

confidence: 99%

Enhancing the linearity characteristics of photoelectric displacement sensor based on extreme learning machine method

Sethuramalingam

Subbiah

2015

Photonic Sens

View full text Add to dashboard Cite

Photoelectric displacement sensors rarely possess a perfectly linear transfer characteristic, but always have some degree of non-linearity over their range of operation. If the sensor output is nonlinear, it will produce a whole assortment of problems. This paper presents a method to compensate the nonlinearity of the photoelectric displacement sensor based on the extreme learning machine (ELM) method which significantly reduces the amount of time needed to train a neural network with the output voltage of the optical displacement sensor and the measured input displacement to eliminate the nonlinear errors in the training process. The use of this proposed method was demonstrated through computer simulation with the experimental data of the sensor. The results revealed that the proposed method compensated the presence of nonlinearity in the sensor with very low training time, lowest mean squared error (MSE) value, and better linearity. This research work involved less computational complexity, and it behaved a good performance for nonlinearity compensation for the photoelectric displacement sensor and has a good application prospect.

show abstract

“…Theorem 2. In this theorem, Annema et al [28] provide any small positive value ε > 0 and activation function g pxq : R Ñ R that is extremely differentiable in every specification; there exists L ď N such that for N arbitrary distinct input vectors tx i |x i P R n , i " 1, . .…”

Section: Concept Of Elmmentioning

confidence: 99%

“…Huang, et al [17] introduced ELM method for Single Layer Feed-forward Neural Network (SLFN) design as a learning algorithm tool [17,27,28]. The ELM algorithm has more effective general ability with faster learning speed.…”

Section: Extreme Learning Machinementioning

confidence: 99%

Estimation of Tsunami Bore Forces on a Coastal Bridge Using an Extreme Learning Machine

Mazinani

Ismail

Shamshirband

et al. 2016

Entropy

View full text Add to dashboard Cite

This paper proposes a procedure to estimate tsunami wave forces on coastal bridges through a novel method based on Extreme Learning Machine (ELM) and laboratory experiments. This research included three water depths, ten wave heights, and four bridge models with a variety of girders providing a total of 120 cases. The research was designed and adapted to estimate tsunami bore forces including horizontal force, vertical uplift and overturning moment on a coastal bridge. The experiments were carried out on 1:40 scaled concrete bridge models in a wave flume with dimensions of 24 mˆ1.5 mˆ2 m. Two six-axis load cells and four pressure sensors were installed to the base plate to measure forces. In the numerical procedure, estimation and prediction results of the ELM model were compared with Genetic Programming (GP) and Artificial Neural Networks (ANNs) models. The experimental results showed an improvement in predictive accuracy, and capability of generalization could be achieved by the ELM approach in comparison with GP and ANN. Moreover, results indicated that the ELM models developed could be used with confidence for further work on formulating novel model predictive strategy for tsunami bore forces on a coastal bridge. The experimental results indicated that the new algorithm could produce good generalization performance in most cases and could learn thousands of times faster than conventional popular learning algorithms. Therefore, it can be conclusively obtained that utilization of ELM is certainly developing as an alternative approach to estimate the tsunami bore forces on a coastal bridge.

show abstract

Precision requirements for single-layer feedforward neural networks

Cited by 18 publications

References 9 publications

Analog weight adaptation hardware

Analog weight adaptation hardware

Enhancing the linearity characteristics of photoelectric displacement sensor based on extreme learning machine method

Estimation of Tsunami Bore Forces on a Coastal Bridge Using an Extreme Learning Machine

Contact Info

Product

Resources

About