284 citations · 666 across the 17 of their papers we have counts for
4 papers · 1 filter
NAIS-Net: Stable Deep Networks from Non-Autonomous Differential Equations
Marco Ciccone, Marco Gallieri, Jonathan Masci +2
This paper introduces Non-Autonomous Input-Output Stable Network(NAIS-Net), a very deep architecture where each stacked processing block is derived from a time-invariant non-autono…
Understanding Locally Competitive Networks
Rupesh Kumar Srivastava, Jonathan Masci, Faustino Gomez +1
Recently proposed neural network activation functions such as rectified linear, maxout, and local winner-take-all have allowed for faster and more effective training of deep neural…
A Clockwork RNN
Jan Koutník, Klaus Greff, Faustino Gomez +1
Sequence prediction and classification are ubiquitous and challenging problems in machine learning that can require identifying complex dependencies between temporally distant inpu…
Evolino for recurrent support vector machines
Juergen Schmidhuber, Matteo Gagliolo, Daan Wierstra +1
Traditional Support Vector Machines (SVMs) need pre-wired finite time windows to predict and classify time series. They do not have an internal state necessary to deal with sequenc…