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 *
                            
clc
clear all
close all

% *************************************************************************
% This script reproduces Figure 3B of the manuscript.
%   Florian Raudies, 01/30/2014, Boston University.
%   This script will run for about 620 minutes or 10 hours.
% *************************************************************************

LABEL_SIZE = 16;

nLayer      = 3;
nHidden     = 40;
nRun        = 50;
NBlock      = [100 150 200 300 400 800];
nNBlock     = length(NBlock);
dcl         = DoubleContextLearnerMLP({'A','B','C','D'},...
                                      {'1','2','3','4'},nHidden);
Err  = zeros(nRun,nNBlock);
tic
for iRun = 1:nRun,
    % Set seed for random number generator to be able to replicate data.
    rng(1+iRun);
    fprintf('Working on run %d of %d.\n',iRun,nRun);
    for iBlock = 1:nNBlock,
        fprintf('Working on block number %d of %d.\n',iBlock,nNBlock);
        nBlock = NBlock(iBlock);
        dcl.learn(nBlock,{'A1','B1'});
        Err(iRun,iBlock) = dcl.testError;
    end
end
toc

nSample = size(Err,1);
sErr    = 1/sqrt(nSample);
id      = dcl.getIdentifier();

figure('Position',[50 50 600 500],'PaperPosition',[2 2 5 4],'Name','3B');
bar(1:nNBlock,mean(Err,1),'FaceColor',[0.7 0.7 0.7]); hold on;
errorbar(1:nNBlock,mean(Err,1),sErr*std(Err,0,1),'k.',...
        'LineWidth',1.5); hold off;
xlabel('Number of blocks','FontSize',LABEL_SIZE);
ylabel('Error probability','FontSize',LABEL_SIZE);
title(id,'FontSize',LABEL_SIZE);
set(gca,'XTickLabel',num2cellstr(NBlock),'FontSize',LABEL_SIZE);
axis([0 nNBlock+1 0 0.55]); axis square;