We tested a rule generalization capability with a Deep Belief Network (DBN), Multi-Layer Perceptron network, and the combination of a DBN with a linear perceptron (LP). Overall, the combination of the DBN and LP had the highest success rate for generalization.
Model Type: Connectionist Network
Simulation Environment: MATLAB
Implementer(s): Raudies, Florian [florian.raudies at gmail.com]
References:
Raudies F, Zilli EA, Hasselmo ME. (2014). Deep belief networks learn context dependent behavior. PloS one. 9 [PubMed]