Biologically-Motivated Deep Learning Method using Hierarchical Competitive Learning
This method addresses the challenge of training CNNs with poorly labeled data, such as in time series or medical applications, though it appears incremental as it builds on existing biologically-inspired techniques.
The study tackled the problem of deep convolutional neural networks requiring large labeled datasets by proposing a biologically-motivated unsupervised competitive learning method for pre-training, achieving state-of-the-art performance on ImageNet as a biologically-motivated approach.
This study proposes a novel biologically-motivated learning method for deep convolutional neural networks (CNNs). The combination of CNNs and back propagation (BP) learning is the most powerful method in recent machine learning regimes. However, it requires large labeled data for training, and this requirement can occasionally become a barrier for real world applications. To address this problem and utilize unlabeled data, I propose to introduce unsupervised competitive learning which only requires forward propagating signals as a pre-training method for CNNs. The method was evaluated by image discrimination tasks using MNIST, CIFAR-10, and ImageNet datasets, and it achieved a state-of-the-art performance as a biologically-motivated method in the ImageNet experiment. The results suggested that the method enables higher-level learning representations solely from forward propagating signals without a backward error signal for the learning of convolutional layers. The proposed method could be useful for a variety of poorly labeled data, for example, time series or medical data.