论文标题
四元基因估算的复发性投影神经网络在单位四个
Quaternion-Valued Recurrent Projection Neural Networks on Unit Quaternions
论文作者
论文摘要
超复杂值的神经网络，包括四元素值神经网络，可以将多维数据视为单个实体。在本文中，我们介绍了Quaternion值重复投影神经网络（QRPNNS）。简而言之，QRPNN是通过将非本地投影学习与四个值相关的相关神经网络（QRCNN）相结合的。我们表明QRPNNS克服了QRCNN的串扰问题。因此，它们适合实施关联记忆。此外，计算实验表明，QRPNNs比相应的QRCNN具有更大的存储容量和噪声耐受性。
Hypercomplex-valued neural networks, including quaternion-valued neural networks, can treat multi-dimensional data as a single entity. In this paper, we present the quaternion-valued recurrent projection neural networks (QRPNNs). Briefly, QRPNNs are obtained by combining the non-local projection learning with the quaternion-valued recurrent correlation neural network (QRCNNs). We show that QRPNNs overcome the cross-talk problem of QRCNNs. Thus, they are appropriate to implement associative memories. Furthermore, computational experiments reveal that QRPNNs exhibit greater storage capacity and noise tolerance than their corresponding QRCNNs.
