- We present a connectionist model that combines motions and language based on the behavioral experiences of a real robot. Two models of recurrent neural network with parametric bi...
Tetsuya Ogata, Masamitsu Murase, Jun Tani, Kazunor...
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
Spiking neural networks are computationally more powerful than conventional artificial neural networks. Although this fact should make them especially desirable for use in evoluti...
Rich Drewes, James B. Maciokas, Sushil J. Louis, P...
We present several modifications of the original recurrent neural network language model (RNN LM). While this model has been shown to significantly outperform many competitive l...
Tomas Mikolov, Stefan Kombrink, Lukas Burget, Jan ...
Many real-world sequence learning tasks require the prediction of sequences of labels from noisy, unsegmented input data. In speech recognition, for example, an acoustic signal is...