Learning invariance from transformation sequences
Neural Computation
Self-organization of shift-invariant receptive fields
Neural Networks
Slow feature analysis: unsupervised learning of invariances
Neural Computation
Synergies Between Intrinsic and Synaptic Plasticity Mechanisms
Neural Computation
Robust Object Recognition with Cortex-Like Mechanisms
IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning Natural Image Structure with a Horizontal Product Model
ICA '09 Proceedings of the 8th International Conference on Independent Component Analysis and Signal Separation
Self-organization of topographic bilinear networks for invariant recognition
Neural Computation
| Hi-index | 0.00 |
The visual system processes the features and movement of an object in separate pathways, called the ventral and dorsal streams. To integrate this principle in a functional model, a recurrent predictive network with a horizontal product is introduced. Learned in an unsupervised manner, two sets of hidden units represent cells in the ventral and dorsal pathways, respectively. Experiments show that the activity in the ventral-like units persists, given that the same feature appears in the receptive field, whilst the activity in the dorsal-like units shows a fluctuating pattern with different directions of object movements. Moreover, we show that the position information predicts the input's future position taking into account its moving direction due to the direction-selective responses of the dorsal-like units.