Analyzing bilinear neural networks with new curve fitting for application to human motion analysis

Ito, Toshio; Senta, Yosuke; Nagashima, Fumio

doi:10.1109/icsmc.2012.6377725

Cited by 3 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is possible to represent simultaneous linear or nonlinear differential equations using BNNs. Moreover, as shown in [3], it is possible to analyze the output functions from all neurons in a given BNN system unlike the given NN model. As analysis for a weak nonlinear model, BNN systems are useful for human motion analysis.…”

Section: Introductionmentioning

confidence: 99%

“…As analysis for a weak nonlinear model, BNN systems are useful for human motion analysis. As one example of human motion, the walking motion is analyzed by using the acceleration data outputted from the accelerometer embedded in a mobile phone and BNN systems in [3]. BNN systems are currently adopted in the pedometers for humans; furthermore those are adopted in the pedometers for dogs [4].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Supervised Learning Methods of Bilinear Neural Network Systems Using Discrete Data

Ito¹

2016

IJMLC

Self Cite

View full text Add to dashboard Cite

This paper presents supervised learning methods of neural networks called bilinear neural networks with time delay (BNN). A BNN system was proposed to analyze a weak nonlinear model. In this paper, we propose supervised learning methods of BNN systems using discrete data and continuous curves of the data obtained by curve fitting. We introduce a method for fitting a finite Fourier series to discrete data and show that the fitted curve can be created as the output from a BNN system. By using this fitting method, we propose a method for determining the optimal values for the coefficients of all connections for each neuron in BNN systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%