Oct 31, 2016 · We propose a convolutional recurrent neural network, with Winner-Take-All dropout for high dimensional unsupervised feature learning in multi- ...

Sep 1, 2017 · We propose a convolutional recurrent neural network (ConvRNNs), with winner-take-all (WTA) dropout for high-dimensional unsupervised feature ...

A scalable reinterpretation of the Deep Predictive Coding Networks trained end-to-end with backpropagation through time, an extension of the previously ...

Jul 18, 2018 · We apply the proposed method for object recognition using temporal context in videos and obtain better results than comparable methods in the ...

We propose a convolutional recurrent neural network, with Winner-Take-All dropout for high dimensional unsupervised feature learning in multi-dimensional ...

Mar 15, 2017 · We propose a convolutional recurrent neural network, with Winner-Take-All dropout for high dimensional unsupervised feature.

Exploiting Spatio-Temporal Structure with Recurrent Winner-Take-All Networks ... We propose a convolutional recurrent neural network, with Winner-Take-All dropout ...

摘要. We propose a convolutional recurrent neural network (ConvRNNs), with winner-take-all (WTA) dropout for high-dimension.

We propose a convolutional recurrent neural network, with Winner-Take-All dropout for high dimensional unsupervised feature learning in multi-dimensional time ...

Exploiting spatio-temporal structure with recurrent winner-take-all networks. E Santana, MS Emigh, P Zegers, JC Principe. IEEE Transactions on Neural Networks ...