@Override public Matrix apply(Matrix in) { final Matrix out = DMF.copyMatrix(in); for (int i = 0; i < in.getNumRows(); i++) { for (int j = 0; j < in.getNumColumns(); j++) { out.setElement(i, j, gPrime.apply(in.getElement(i, j))); } } return out; }
@Override public Matrix apply(Matrix in) { final Matrix out = DMF.copyMatrix(in); for (int i = 0; i < in.getNumRows(); i++) { for (int j = 0; j < in.getNumColumns(); j++) { out.setElement(i, j, gPrime.apply(in.getElement(i, j))); } } return out; }
@Override public Matrix apply(Matrix in) { final Matrix out = DMF.copyMatrix(in); for (int i = 0; i < in.getNumRows(); i++) { for (int j = 0; j < in.getNumColumns(); j++) { out.setElement(i, j, g.apply(in.getElement(i, j))); } } return out; }
@Override public Matrix apply(Matrix in) { final Matrix out = DMF.copyMatrix(in); for (int i = 0; i < in.getNumRows(); i++) { for (int j = 0; j < in.getNumColumns(); j++) { out.setElement(i, j, g.apply(in.getElement(i, j))); } } return out; }
Matrix u = learner.getU(); Matrix w = learner.getW(); Matrix bias = MatrixFactory.getDenseDefault().copyMatrix(learner.getBias()); BilinearEvaluator eval = new RootMeanSumLossEvaluator(); eval.setLearner(learner);
final Matrix u = learner.getU(); final Matrix w = learner.getW(); final Matrix bias = MatrixFactory.getDenseDefault().copyMatrix(learner.getBias()); final BilinearEvaluator eval = new RootMeanSumLossEvaluator(); eval.setLearner(learner);
final Matrix bias = MatrixFactory.getDenseDefault().copyMatrix(learner.getBias()); final BilinearEvaluator eval = new RootMeanSumLossEvaluator(); eval.setLearner(learner);