Abstract | ||
---|---|---|
The recognition of continuous dimensional emotion remains a challenging task due to large variations in the expression of emotion, and the difficulty of modeling emotion as temporal processes. This work proposes the use of a Nonlinear AutoRegressive with eXogenous inputs recurrent neural network (NARX-RNN) to learn emotional patterns in a given a dataset. The application of particle swarm optimisation in training the NARX-RNN is considered and compared to a gradient descent algorithm. We show that the NARX-RNN outperforms other methods in its emotion recognition ability, and can be easily trained with both gradient-free and gradient-based optimization methods. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/ACII.2015.7344599 | ACII |
Keywords | Field | DocType |
particle swarm optimization, recurrent neural networks, affective computing | Particle swarm optimization,Autoregressive model,Gradient descent,Nonlinear autoregressive exogenous model,Pattern recognition,Computer science,Recurrent neural network,Time delay neural network,Artificial intelligence,Affective computing,Artificial neural network | Conference |
ISSN | Citations | PageRank |
2156-8103 | 1 | 0.36 |
References | Authors | |
16 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ntombikayise Banda | 1 | 69 | 4.09 |
Andries P. Engelbrecht | 2 | 660 | 61.64 |
Peter Robinson | 3 | 1438 | 129.42 |