We propose to address the issue of sample efficiency, in Deep Convolutional Neural Networks (DCNN), with a semi-supervised training strategy that combines Hebbian learning with gradient descent: all internal layers (both convolutional and fully connected) are pre-trained using an unsupervised approach based on Hebbian learning, and the last fully connected layer (the classification layer) is trained using Stochastic Gradient Descent (SGD). In fact, as Hebbian learning is an unsupervised learning method, its potential lies in the possibility of training the internal layers of a DCNN without labels. Only the final fully connected layer has to be trained with labeled examples. We performed experiments on various object recognition datasets, in different regimes of sample efficiency, comparing our semi-supervised (Hebbian for internal layers + SGD for the final fully connected layer) approach with end-to-end supervised backprop training, and with semi-supervised learning based on Variational Auto-Encoder (VAE). The results show that, in regimes where the number of available labeled samples is low, our semi-supervised approach outperforms the other approaches in almost all the cases.

翻译：我们提议在深革命神经网络(DCNN)中解决抽样效率问题,采用半监督培训战略,将赫比亚学习与梯度下降相结合:所有内部层(共和和完全连接)都采用基于赫比亚学习的未经监督的方法接受预先培训,而最后一个完全连接的层(分类层)则使用托盘级梯级(SGD)培训。事实上,赫比亚学习是一种不受监督的学习方法,其潜力在于培训一个无标签的DCNN内部层的可能性。只有最终完全连接的层才需要用贴标签的例子进行培训。我们在不同的抽样效率制度中对各种对象识别数据集进行了实验,将我们的半监督(内层赫比亚+SGD,最后完全连接层)方法与端对端监督的背层培训进行比较,并以Variational Aut-Ecorder(VAE)为基础进行半监督学习。结果显示,在体制中,所有标签样本的数量几乎都是低的,我们的半监督式方法。