Sciweavers

6 search results - page 1 / 2
» Online Processing of Multiple Inputs in a Sparsely-Connected...
Sort
View
ICANN
2003
Springer
14 years 4 months ago
Online Processing of Multiple Inputs in a Sparsely-Connected Recurrent Neural Network
The storage and short-term memory capacities of recurrent neural networks of spiking neurons are investigated. We demonstrate that it is possible to process online many superimpose...
Julien Mayor, Wulfram Gerstner
ICANN
2009
Springer
14 years 5 months ago
Combining Multiple Inputs in HyperNEAT Mobile Agent Controller
In this paper we present neuro-evolution of neural network controllers for mobile agents in a simulated environment. The controller is obtained through evolution of hypercube encod...
Jan Drchal, Ondrej Kapral, Jan Koutník, Mir...
ICANN
2007
Springer
14 years 5 months ago
Multi-dimensional Recurrent Neural Networks
Abstract. Recurrent neural networks (RNNs) have proved effective at one dimensional sequence learning tasks, such as speech and online handwriting recognition. Some of the properti...
Alex Graves, Santiago Fernández, Jürge...
TNN
2008
138views more  TNN 2008»
13 years 11 months ago
A Fast and Scalable Recurrent Neural Network Based on Stochastic Meta Descent
This brief presents an efficient and scalable online learning algorithm for recurrent neural networks (RNNs). The approach is based on the real-time recurrent learning (RTRL) algor...
Zhenzhen Liu, Itamar Elhanany
NECO
2010
147views more  NECO 2010»
13 years 9 months ago
Connectivity, Dynamics, and Memory in Reservoir Computing with Binary and Analog Neurons
Abstract: Reservoir Computing (RC) systems are powerful models for online computations on input sequences. They consist of a memoryless readout neuron which is trained on top of a ...
Lars Büsing, Benjamin Schrauwen, Robert A. Le...