用单矩阵结构的回路网络提升神经演化效率，适合超边缘设备
Introducing Echo Networks for Computational Neuroevolution
- 采用连接矩阵表示网络，无分层结构，支持双向递归连接
- 在心电图分类任务中表现良好，仅用几十个神经元实现高精度
- 基因组为单一矩阵，便于矩阵运算作突变重组，适合系统化演化
针对极边缘场景，仅需数十个人工神经元即可实现离散时间信号事件检测与分类的理想需求。尽管前馈网络、RNN 和 CNN 通过演化算法可成功达成目标，但若使用标准权重直接编码（如经典 NEAT 算法），则难以实现突变与重组的系统性。为此，我们提出 Echo Networks——一种仅由连接矩阵构成的循环网络：突触源神经元作为行，目标神经元作为列，权重为矩阵元素。无层级结构，连接可双向且均为递归。输入输出可任意分配至任一神经元，仅需额外可选函数（如 sigmoid）生成二分类输出。我们在心电图信号分类任务中成功验证了其有效性，最突出潜力在于其基因组为单一矩阵表示，支持矩阵运算与分解作为突变和重组算子。
原文摘要 · Abstract (English)
For applications on the extreme edge, minimal networks of only a few dozen artificial neurons for event detection and classification in discrete time signals would be highly desirable. Feed-forward networks, RNNs, and CNNs evolved through evolutionary algorithms can all be successful in this respect but pose the problem of allowing little systematicity in mutation and recombination if the standard direct genetic encoding of the weights is used (as for instance in the classic NEAT algorithm). We therefore introduce Echo Networks, a type of recurrent network that consists of the connection matrix only, with the source neurons of the synapses represented as rows, destination neurons as columns and weights as entries. There are no layers, and connections between neurons can be bidirectional but are technically all recurrent. Input and output can be arbitrarily assigned to any of the neurons and only use an additional (optional) function in their computational path, e.g., a sigmoid to obtain a binary classification output. We evaluated Echo Networks successfully on the classification of electrocardiography signals but see the most promising potential in their genome representation as a single matrix, allowing matrix computations and factorisations as mutation and recombination operators.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。