Neural-network models: Predicting spontaneous recovery of memory
โ Scribed by Stone, James V.; Hunkin, Nicola M.; Hornby, Angela
- Book ID
- 109776545
- Publisher
- Nature Publishing Group
- Year
- 2001
- Tongue
- English
- Weight
- 130 KB
- Volume
- 414
- Category
- Article
- ISSN
- 0028-0836
- DOI
- 10.1038/35102676
No coin nor oath required. For personal study only.
๐ SIMILAR VOLUMES
Neural networks have proved to be useful models of associative memories. After a brief review of the standard Hopfield model we discuss how to introduce some realistic features such as categorization of the stored information and asymmetric synapsis.
Figure 1 Left: Original network with excitatory (red) and inhibitory connections (blue). Middle: Inferred connectivity using kinetic Ising models with memory. Colors mark their connection strengths. Right: Radio operating characteristics (ROC) curves of inferred excitatory connections.