Publication | Closed Access
A fast fixed point learning method to implement associative memory on CNNs
35
Citations
6
References
1997
Year
Convolutional Neural NetworkEngineeringMachine LearningNeural Networks (Machine Learning)Interconnection WeightsRecurrent Neural NetworkSocial SciencesSparse Neural NetworkEmbedded Machine LearningAssociative MemoryCellular Neural NetworksComputer EngineeringComputer ScienceNeural Networks (Computational Neuroscience)Deep LearningNeural Architecture SearchComputer VisionFast Fixed PointComputational NeuroscienceCellular Neural NetworkBrain-like ComputingStorage Capacity
Cellular Neural Networks (CNNs) with space-varying interconnections are considered here to implement associative memories. A fast learning method is presented to compute the interconnection weights. The algorithm was carefully tested and compared to other methods. Storage capacity, noise immunity, and spurious state avoidance capability of the proposed system are discussed.
| Year | Citations | |
|---|---|---|
Page 1
Page 1