Efficient Convolutional Neural Network Training with Direct Feedback Alignment
This work addresses the challenge of efficient and accurate CNN training for scenarios with limited data, though it is incremental as it builds on existing DFA methods.
The paper tackled the problem of low training performance of direct feedback alignment (DFA) in convolutional neural networks by combining it with back-propagation and proposing binary DFA to reduce computational cost, achieving better performance than conventional BP in tasks like CIFAR-10/100 and object tracking, especially with small datasets.
There were many algorithms to substitute the back-propagation (BP) in the deep neural network (DNN) training. However, they could not become popular because their training accuracy and the computational efficiency were worse than BP. One of them was direct feedback alignment (DFA), but it showed low training performance especially for the convolutional neural network (CNN). In this paper, we overcome the limitation of the DFA algorithm by combining with the conventional BP during the CNN training. To improve the training stability, we also suggest the feedback weight initialization method by analyzing the patterns of the fixed random matrices in the DFA. Finally, we propose the new training algorithm, binary direct feedback alignment (BDFA) to minimize the computational cost while maintaining the training accuracy compared with the DFA. In our experiments, we use the CIFAR-10 and CIFAR-100 dataset to simulate the CNN learning from the scratch and apply the BDFA to the online learning based object tracking application to examine the training in the small dataset environment. Our proposed algorithms show better performance than conventional BP in both two different training tasks especially when the dataset is small.