Name
Title | ||
|---|---|---|
Periodic Motions, Mapping Ordered Sequences, and Training of Dynamic Neural Networks to Generate Continuous and Discontinuous Trajectories |
Abstract | ||
|---|---|---|
Designing efficient methods for training dynamic neural networks for learning spatio-temporal patterns is of great interest at present. In particular, the 驴trajectory generation problem驴 that involves training the network to learn and replicate autonomously a specified time-varying periodic motion has attracted considerable recent attention. A novel systematic approach to solve this problem by decomposing the overall task into two sub-tasks, a spatio-temporal sequence assignment and a mapping of ordered sequences, is presented in this paper. This decomposition permits the dynamic neural network to be realized as a cascade of a simple recurrent net followed by a non-recurrent one that yields considerable reduction in training complexity. A detailed performance evaluation of the present scheme is given by considering several trajectory generation experiments that highlight the strong points of this approach, which include simplicity and accuracy in training, flexibility to include control parameters in order to modify on-line the shape of the trajectory learned and the speed of repetition along a cyclic trajectory, and the possibility of learning both continuous and discontinuous trajectory patterns. |
Year | DOI | Venue |
|---|---|---|
2000 | 10.1109/IJCNN.2000.861273 | IJCNN (3) |
Keywords | Field | DocType |
considerable recent attention,ordered sequences,discontinuous trajectories,training complexity,trajectory generation problem,generate continuous,discontinuous trajectory pattern,periodic motions,present scheme,dynamic neural network,novel systematic approach,cyclic trajectory,dynamic neural networks,trajectory generation experiment,spatio-temporal pattern,recurrent neural networks,network synthesis,computer networks,function approximation,pattern recognition,neural networks,learning artificial intelligence | Periodic function,Computer science,Types of artificial neural networks,Time delay neural network,Cascade,Artificial intelligence,Deep learning,Artificial neural network,Periodic graph (geometry),Trajectory,Machine learning | Conference |
ISSN | ISBN | Citations |
1098-7576 | 0-7695-0619-4 | 3 |
PageRank | References | Authors |
0.42 | 6 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Pablo Zegers | 1 | 35 | 6.32 |
| Malur K. Sundareshan | 2 | 197 | 55.32 |