Sigma-Pi learning: on radial basis functions and cortical associative learning
Advances in neural information processing systems 2
A Bayesian analysis of self-organizing maps
Neural Computation
Learning Synaptic Clusters for Nonlinear Dendritic Processing
Neural Processing Letters
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Self-Organizing Maps
Bilinear Sparse Coding for Invariant Vision
Neural Computation
Dynamic Link Matching between Feature Columns for Different Scale and Orientation
Neural Information Processing
Learning of Neural Information Routing for Correspondence Finding
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
A marker-based model for the ontogenesis of routing circuits
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
| Hi-index | 0.01 |
By frame of reference transformations, an input variable in one coordinate system is transformed into an output variable in a different coordinate system depending on another input variable. If the variables are represented as neural population codes, then a sigma-pi network is a natural way of coding this transformation. By multiplying two inputs it detects coactivations of input units, and by summing over the multiplied inputs, one output unit can respond invariantly to different combinations of coactivated input units. Here, we present a sigma-pi network and a learning algorithm by which the output representation self-organizes to form a topographic map. This network solves the frame of reference transformation problem by unsupervised learning.