A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2011; you can also visit the original URL.
The file type is application/pdf
.
Approaches Based on Markovian Architectural Bias in Recurrent Neural Networks
[chapter]
2004
Lecture Notes in Computer Science
Recent studies show that state-space dynamics of randomly initialized recurrent neural network (RNN) has interesting and potentially useful properties even without training. More precisely, when initializing RNN with small weights, recurrent unit activities reflect history of inputs presented to the network according to the Markovian scheme. This property of RNN is called Markovian architectural bias. Our work focuses on various techniques that make use of architectural bias. The first
doi:10.1007/978-3-540-24618-3_22
fatcat:vm5ogwcvuzczfpfswior6tmm7u