IEEE Trans Neural Netw Learn Syst. 2019 Oct;30(10):3186-3199. doi: 10.1109/TNNLS.2018.2890658. Epub 2019 Jan 28.
In this paper, we introduce a neural network (NN) model named clone-based neural network (CbNN) to design associative memories. Neurons in CbNN can be cloned statically or dynamically which allows to increase the number of data that can be stored and retrieved. Thanks to their plasticity, CbNN can handle correlated information more robustly than existing models and thus provides better memory capacity. We experiment this model in encoded neural networks also known as Gripon-Berrou NNs. Numerical simulations demonstrate that memory and recall abilities of CbNN outperform state of the art for the same memory footprint.
在本文中，我们引入了一种名为基于克隆的神经网络（CbNN）的神经网络模型，用于设计联想存储器。CbNN 中的神经元可以静态或动态地克隆，这允许增加可以存储和检索的数据量。由于其可塑性，CbNN 比现有模型更能稳健地处理相关信息，从而提供更好的存储容量。我们在编码神经网络中也实验了这种模型，称为 Gripon-Berrou 神经网络。数值模拟表明，在相同的存储容量下，CbNN 的存储和检索能力优于现有技术。
