论文标题
使用层次竞争学习的生物学动机深度学习方法
Biologically-Motivated Deep Learning Method using Hierarchical Competitive Learning
论文作者
论文摘要
这项研究提出了一种针对深卷积神经网络（CNN）的新型生物动机学习方法。 CNN和背部传播（BP）学习的结合是最近机器学习制度中最强大的方法。但是，它需要大量标记的数据进行培训，这一要求有时可能会成为现实世界应用的障碍。为了解决这个问题并利用未标记的数据，我建议引入无监督的竞争学习，这只需要向前传播信号作为CNN的预训练方法。使用MNIST，CIFAR-10和Imagenet数据集评估该方法，并在Imagenet实验中以生物学动力的方法达到了最先进的性能。结果表明，该方法仅来自前向传播信号而没有向后误差信号来学习卷积层。提出的方法对于标记不佳的数据，例如时间序列或医疗数据可能很有用。
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.
