A winner-take-all Lotka–Volterra recurrent neural network with only one winner in each row and each column

Zheng, Bo

doi:10.1007/s00521-013-1412-0

Cited by 1 publication

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In winner-takes-all, the cluster center closest to the current image hidden layer activity is chosen as the Layer 2 sample among the cluster centers from computed class hypotheses. Accordingly, only one cluster wins to be fed-back into the hidden layer activity (see [71] for the effect of winner-takes-all behavior in neural networks). In average scheme, the cluster centers from different hypotheses are averaged and fed back into the hidden Layer 2 activity.…”

Section: Number Of Hypotheses and Competitionmentioning

confidence: 99%

Classification of Occluded Objects Using Fast Recurrent Processing

Yılmaz

2015

2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA)

View full text Add to dashboard Cite

Recurrent neural networks are powerful tools for handling incomplete data problems in computer vision, thanks to their significant generative capabilities. However, the computational demand for these algorithms is too high to work in real time, without specialized hardware or software solutions. In this paper, we propose a framework for augmenting recurrent processing capabilities into a feedforward network without sacrificing much from computational efficiency. We assume a mixture model and generate samples of the last hidden layer according to the class decisions of the output layer, modify the hidden layer activity using the samples, and propagate to lower layers. For visual occlusion problem, the iterative procedure emulates feedforward-feedback loop, filling-in the missing hidden layer activity with meaningful representations. The proposed algorithm is tested on a widely used dataset, and shown to achieve 2× improvement in classification accuracy for occluded objects. When compared to Restricted Boltzmann Machines, our algorithm shows superior performance for occluded object classification.

show abstract

Section: Number Of Hypotheses and Competitionmentioning

confidence: 99%

Classification of Occluded Objects Using Fast Recurrent Processing

Yılmaz

2015

2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA)

View full text Add to dashboard Cite

show abstract

A winner-take-all Lotka–Volterra recurrent neural network with only one winner in each row and each column

Cited by 1 publication

References 19 publications

Classification of Occluded Objects Using Fast Recurrent Processing

Classification of Occluded Objects Using Fast Recurrent Processing

Contact Info

Product

Resources

About