论文标题
深层储层网络，具有直接反馈对齐的学识渊博的隐藏储层权重
Deep Reservoir Networks with Learned Hidden Reservoir Weights using Direct Feedback Alignment
论文作者
论文摘要
深度储层计算已成为深度学习的新范式，该范式基于储层计算原理，该原理是维持神经元与层次深度学习的随机池。储层范式反映并尊重生物学大脑中的高度复发，以及神经元动力学在学习中的作用。但是，一个阻碍深层储层网络开发的问题是，一个人不能通过储层层倒流。最近的深层储层架构与深层神经网络相同的方式学习了隐藏或分层的表示，而是将所有隐藏的水库融合在一起以执行传统的回归。在这里，我们为时间序列的预测和分类提供了一个新颖的深层储层网络，该网络使用具有生物学启发的反向传播替代方案，通过非差异的隐藏储层层来学习，称为直接反馈对齐，类似于大脑中的全球多巴胺信号。我们在两个现实世界中的多维时间序列数据集上演示了其功效。
Deep Reservoir Computing has emerged as a new paradigm for deep learning, which is based around the reservoir computing principle of maintaining random pools of neurons combined with hierarchical deep learning. The reservoir paradigm reflects and respects the high degree of recurrence in biological brains, and the role that neuronal dynamics play in learning. However, one issue hampering deep reservoir network development is that one cannot backpropagate through the reservoir layers. Recent deep reservoir architectures do not learn hidden or hierarchical representations in the same manner as deep artificial neural networks, but rather concatenate all hidden reservoirs together to perform traditional regression. Here we present a novel Deep Reservoir Network for time series prediction and classification that learns through the non-differentiable hidden reservoir layers using a biologically-inspired backpropagation alternative called Direct Feedback Alignment, which resembles global dopamine signal broadcasting in the brain. We demonstrate its efficacy on two real world multidimensional time series datasets.
