Abstract—A feed-forward loop has been widely used in
control systems to boost the performance without hurting the
overall stability of the system. We propose a new neural network,
FfcNet by adopting the idea from the control theory. The
proposed network adds a pre-designed feed-forward loop in
parallel with the existing regular blocks, which is similar to the
identity mapping in ResNet network. The feed-forward loop
helps the overall network to converge faster while keeping
overall system stability and accuracy. It is also shown that the
feed-forward loop is equivalent to setting a proper initial
condition of the parameters in the network. A special dataset of
highly distorted 7-segment LED images is prepared to evaluate
the performance of the pattern recognition algorithm. We
demonstrated the performance of the proposed design through
simulations and found the new design improved the convergence
rate by 52% from the original ResNet network while keeping the
same test accuracy.
Index Terms——Fast convergence, feed-forward loop, FfcNet,
pattern recognition, ResNet.
Nam Guk Kim is with Cybernetics Imaging Systems, Changwon,
Gyeongsangnam-do, Korea, 51391 (e-mail: ngkim823@gmail.com).
Cite: Nam Guk Kim, "A New Approach to Neural Network Design for Fast Convergence via Feed-forward Loop," International Journal of Machine Learning and Computing vol. 12, no. 5, pp. 259-265, 2022.
Copyright @ 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).