Sciweavers

299 search results - page 53 / 60
» Multi-dimensional Recurrent Neural Networks
Sort
View
NN
2002
Springer
105views Neural Networks» more  NN 2002»
13 years 9 months ago
The computational role of dopamine D1 receptors in working memory
The prefrontal cortex (PFC) is essential for working memory, which is the ability to transiently hold and manipulate information necessary for generating forthcoming action. PFC n...
Daniel Durstewitz, Jeremy K. Seamans
FOCI
2007
IEEE
14 years 4 months ago
Opposite Transfer Functions and Backpropagation Through Time
— Backpropagation through time is a very popular discrete-time recurrent neural network training algorithm. However, the computational time associated with the learning process t...
Mario Ventresca, Hamid R. Tizhoosh
NPL
2000
99views more  NPL 2000»
13 years 9 months ago
On the Internal Representations of Product Units
This paper explores internal representation power of product units [1] that act as the functional nodes in the hidden layer of a multi-layer feedforward network. Interesting proper...
Jung-Hua Wang, Yi-Wei Yu, Jia-Horng Tsai
TSD
2010
Springer
13 years 7 months ago
Hybrid HMM/BLSTM-RNN for Robust Speech Recognition
The question how to integrate information from different sources in speech decoding is still only partially solved (layered architecture versus integrated search). We investigate t...
Yang Sun, Louis ten Bosch, Lou Boves
ISCC
2007
IEEE
14 years 4 months ago
Long Horizon End-to-End Delay Forecasts: A Multi-Step-Ahead Hybrid Approach
A long horizon end-to-end delay forecast, if possible, will be a breakthrough in traffic engineering. This paper introduces a hybrid approach to forecast end-to-end delays using ...
Vinh Bui, Weiping Zhu, Antonio Pescapè, Ale...