Self-organizing maps
GTM: the generative topographic mapping
Neural Computation
Two topographic maps for data visualisation
Data Mining and Knowledge Discovery
Faster clustering of complex data with the generalised harmonic topographic mapping(G-HaToM)
AIC'05 Proceedings of the 5th WSEAS International Conference on Applied Informatics and Communications
Matching the dimensionality of maps with that of the data
SMO'05 Proceedings of the 5th WSEAS international conference on Simulation, modelling and optimization
Tight clusters and smooth manifolds with the harmonic topographic map
SMO'05 Proceedings of the 5th WSEAS international conference on Simulation, modelling and optimization
Quantization errors in the harmonic topographic mapping
SIP'06 Proceedings of the 5th WSEAS international conference on Signal processing
Local vs global models in pong
ICANN'05 Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II
| Hi-index | 0.00 |
We create a new form of topographic map which is based on a nonlinear mapping of a space of latent points. The mapping of these latent points into data space creates centres which are equivalent to those of the standard SOM. We relate this mapping to the Generative Topographic Mapping, GTM. We then show that it is rather simple and computationally inexpensive to grow one of these maps and that a probabilistic interpretation of these maps facilitates our investigation of alternative algorithms.