Deep belief network learns context dependent behavior (Raudies, Zilli, Hasselmo 2014)

 Download zip file 
Help downloading and running models
Accession:194883
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.
Reference:
1 . Raudies F, Zilli EA, Hasselmo ME (2014) Deep belief networks learn context dependent behavior. PLoS One 9:e93250 [PubMed]
Citations  Citation Browser
Model Information (Click on a link to find other models with that property)
Model Type: Connectionist Network;
Brain Region(s)/Organism:
Cell Type(s):
Channel(s):
Gap Junctions:
Receptor(s):
Gene(s):
Transmitter(s):
Simulation Environment: MATLAB;
Model Concept(s):
Implementer(s): Raudies, Florian [florian.raudies at gmail.com];
/
Matlab
screenshots
README.html
DeepBeliefNetwork.m
DoubleContextLearner.m
DoubleContextLearnerDBN.m
DoubleContextLearnerDBNaLP.m
DoubleContextLearnerMLP.m
DoubleContextTask.m
Figure2.m
Figure3A.m
Figure3B.m
Figure3C.m
Figure3D.m
Figure3E.m
Figure3F.m
Figure3G.m
Figure3H.m
Figure4B.m
Figure4C.m
Figure4D.m
gpl-3.0.txt *
LinearPerceptron.m
logistic.m
MultiLayerPerceptronNetwork.m
num2cellstr.m
RestrictedBoltzmannMachine.m
rotateXLabels.m *
                            
classdef DoubleContextLearner < DoubleContextTask
    % DoubleContextLearner
    % Abstract class for any class that provides learning of the
    % double-context task.
    %   Florian Raudies, 01/30/2014, Boston University.
    methods
        % Constructor.
        function obj = DoubleContextLearner(LetterLabel,NumberLabel)
            obj = obj@DoubleContextTask(LetterLabel,NumberLabel);
        end
    end
    methods (Abstract = true)
        % Learning of the task with the number of blocks nBlock
        % (repititions of the original data) while excluding any
        % stimulus-context combinations listed in ExcludeState.
        obj = learn(obj,nBlock,ExcludeState)
        % Test all stimulus-context combinations and calculate the error
        % rate.
        err = testError(obj)
        % Train the stimulus-context combinations in the same order rather
        % than random order in the different epochs.
        obj = setBlockTrain(obj,flag)
    end
    methods (Abstract = true, Static = true)
        % Get a unique identifier for the learner.
        id = getIdentifier()
    end
end