Skip to content

Update inferenceReLUvec.m #11

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
bkmgit wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Update inferenceReLUvec.m #11

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
47 changes: 31 additions & 16 deletions SparseDeepNeuralNetwork/matlab/inferenceReLUvec.m
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,23 +4,39 @@

% Initialized feature vectors.
Y = Y0;
octaveinfo=exist('octave_config_info');
% If using Matlab take advantage of sparse implementation
% of singleton expansion, otherwise for Octave use
% bsxfun
if(octaveinfo==0)
% Loop through each weight layer W{i}
for i=1:length(W)

% Loop through each weight layer W{i}
for i=1:length(W)
% Propagate through layer.
% Note: using graph convention of A(i,j) means connection from i *to* j,
% that requires *left* multiplication feature *row* vectors.
Z = Y*W{i};
b = bias{i};
% Apply bias to non-zero entries.
Y = Z + sparse(double(logical(Z)) .* b);
% Threshold negative values.
Y(Y < 0) = 0;
end
else
% Loop through each weight layer W{i}
for i=1:length(W)

% Propagate through layer.
% Note: using graph convention of A(i,j) means connection from i *to* j,
% that requires *left* multiplication feature *row* vectors.
Z = Y*W{i};
b = bias{i};

% Apply bias to non-zero entries.
Y = Z + (double(logical(Z)) .* b);

% Threshold negative values.
Y(Y < 0) = 0;

end
% Propagate through layer.
% Note: using graph convention of A(i,j) means connection from i *to* j,
% that requires *left* multiplication feature *row* vectors.
Z = Y*W{i};
b = bias{i};
% Apply bias to non-zero entries.
Y = Z + bsxfun(@(x,y) x .* y,double(logical(Z)),b);
% Threshold negative values.
Y(Y < 0) = 0;
end
endif

return
end
Expand All @@ -31,4 +47,3 @@
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% (c) <2019> Massachusetts Institute of Technology
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%