FIND_GENERALISABILITY: Find the generalisability of a model. Code written by Katherine Smith, 2003 GENERAL [mean_generalisability, std_generalisability] = find_generalisability(model, n_iterations, verbose) INPUT/S -model: The model for which generalisability is calculated. -n_iteration: Number of iterations to control the complexity of this function? -verbose: Verbose flag. OUTPUT/S -mean_generalisability: The mean generalisability. -mean_generalisability: The standard deviation (?) of the generalisability values? PENDING WORK -Resolve meaning of inputs and outputs. -Add more comments to code. KNOWN BUG/S -None. COMMENT/S -Smith: Attempt to reconstruct an unseen example and measure distance from the example (mean squared difference). RELATED FUNCTION/S FIND_SPECIFICITY ABOUT -Created: November 23rd, 2003 -Last update: Novermber 25th, 2003 -Revision: 0.0.2 -Author: R. S. Schestowitz, University of Manchester ==============================================================
0001 function [mean_generalisability, std_generalisability] = find_generalisability(model, n_iterations, verbose) 0002 % FIND_GENERALISABILITY: Find the generalisability of a model. 0003 % 0004 % Code written by Katherine Smith, 2003 0005 % 0006 % GENERAL 0007 % 0008 % [mean_generalisability, std_generalisability] = 0009 % find_generalisability(model, n_iterations, verbose) 0010 % 0011 % INPUT/S 0012 % 0013 % 0014 % -model: 0015 % The model for which generalisability is calculated. 0016 % 0017 % -n_iteration: 0018 % Number of iterations to control the complexity of 0019 % this function? 0020 % 0021 % -verbose: 0022 % Verbose flag. 0023 % 0024 % OUTPUT/S 0025 % 0026 % -mean_generalisability: 0027 % The mean generalisability. 0028 % 0029 % -mean_generalisability: 0030 % The standard deviation (?) of the generalisability values? 0031 % 0032 % PENDING WORK 0033 % 0034 % -Resolve meaning of inputs and outputs. 0035 % -Add more comments to code. 0036 % 0037 % KNOWN BUG/S 0038 % 0039 % -None. 0040 % 0041 % COMMENT/S 0042 % 0043 % -Smith: Attempt to reconstruct an unseen example 0044 % and measure distance from the example 0045 % (mean squared difference). 0046 % 0047 % RELATED FUNCTION/S 0048 % 0049 % FIND_SPECIFICITY 0050 % 0051 % ABOUT 0052 % 0053 % -Created: November 23rd, 2003 0054 % -Last update: Novermber 25th, 2003 0055 % -Revision: 0.0.2 0056 % -Author: R. S. Schestowitz, University of Manchester 0057 % ============================================================== 0058 0059 % search parameters with simplex 0060 % hack in white width for now 0061 0062 verbose='off'; 0063 % RSS, added 8th December 2003 to get eval_1d_app_model_obj_fn to run 0064 0065 white_width = 0.2; 0066 %subs = figure; 0067 for i=1:n_iterations 0068 [imagelist,example,points, his, los] = make_1d_images(1, size(model.intensity_model.pcs(:,1),1), white_width); 0069 [params, scores(i)] = fminsearch(@eval_msd,zeros(1,size(model.params,2)),optimset('Display',verbose,'TolX',0.001,'TolFun',0.001),model,example); 0070 % scores(i) 0071 % difference_image = abs(example - construct_model_example(params, model, 1:50)); 0072 % figure(subs),hold on,subplot(5,1,i),plot(difference_image),gca,title(['score: ' num2str(scores(i))]); 0073 end 0074 mean_generalisability = mean(scores); 0075 std_generalisability = std(scores);