Daniel@0: function H = entropy(v, scale)
Daniel@0: % ENTROPY Entropy log base 2
Daniel@0: % H = entropy(v)
Daniel@0: % If v is a matrix, we compute the entropy of each column
Daniel@0: %
Daniel@0: % % H = entropy(v,1) means we scale the result so that it lies in [0,1]
Daniel@0: 
Daniel@0: if nargin < 2, scale = 0; end
Daniel@0: 
Daniel@0: v = v + (v==0);
Daniel@0: H = -1 * sum(v .* log2(v), 1); % sum the rows
Daniel@0: 
Daniel@0: if scale
Daniel@0:   n = size(v, 1);
Daniel@0:   unif = normalise(ones(n,1));
Daniel@0:   H = H / entropy(unif);
Daniel@0: end