arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1702.07097cs.NEcs.LG
收藏

自适应双向反向传播:面向神经网络中的生物似然误差信号传输

Adaptive Bidirectional Backpropagation: Towards Biologically Plausible Error Signal Transmission in Neural Networks

MIT CSAIL(麻省理工学院计算机科学与人工智能实验室);National University of Singapore(新加坡国立大学)

Hongyin Luo, Jie Fu, James Glass

摘要:

反向传播(BP)算法被认为是训练深度神经网络的事实上的方法。它使用前馈权重的转置以精确的方式将误差从输出层反向传播到隐藏层。然而,有人认为这在生物学上是不合理的,因为在生物神经系统中,具有确切传入权重的反向传播误差信号被认为是不可能的。在这项工作中,我们提出了一个生物学上合理的神经架构的基础上,在神经科学和非对称BP类方法的相关文献范式。具体来说,我们提出了两个双向学习算法与可训练的前馈和反馈权重。前馈权重用于将激活从输入中继到目标输出。反馈权重将误差信号从输出层传递到隐藏层。与其他非对称BP类方法不同的是,反馈权重在我们的框架中也是可塑的,并且经过训练以近似正向激活。初步结果表明,我们的模型优于其他非对称BP类方法的MNIST和CIFAR-10数据集。

英文摘要:

The back-propagation (BP) algorithm has been considered the de-facto method for training deep neural networks. It back-propagates errors from the output layer to the hidden layers in an exact manner using the transpose of the feedforward weights. However, it has been argued that this is not biologically plausible because back-propagating error signals with the exact incoming weights are not considered possible in biological neural systems. In this work, we propose a biologically plausible paradigm of neural architecture based on related literature in neuroscience and asymmetric BP-like methods. Specifically, we propose two bidirectional learning algorithms with trainable feedforward and feedback weights. The feedforward weights are used to relay activations from the inputs to target outputs. The feedback weights pass the error signals from the output layer to the hidden layers. Different from other asymmetric BP-like methods, the feedback weights are also plastic in our framework and are trained to approximate the forward activations. Preliminary results show that our models outperform other asymmetric BP-like methods on the MNIST and the CIFAR-10 datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑