Avoid training certain neurons
조회 수: 7 (최근 30일)
이전 댓글 표시
Using the Deep Learning Toolbox, I wish to construct a simple feed-forward network for a simulation, however assume I have already trained one of the hidden neurons (out of several) with the correct weights and biases and I don't want them to change during training. How can I make this single specific neuron be "constant" and not get retrained with new wights and biases while the rest of the network is being trained?
댓글 수: 0
채택된 답변
Hiro Yoshino
2019년 12월 23일
There is an option to keep specific layers' learning rates low so you can fix them as they are.
for example
fullyConnectedLayer(<outputsize>, 'WeightLearnRateFactor', 0, 'BiasLearnRateFactor', 0)
This way, you would multiply zero to the global learning rate, which is set via trainingOptions function, and thus the learning rates of the weights in the fully-connected-layer are set as zero.
추가 답변 (0개)
참고 항목
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!