论文标题
从协作自我复制器中构建有机网络
Constructing Organism Networks from Collaborative Self-Replicators
论文作者
论文摘要
我们介绍了有机体网络，该网络的功能像单个神经网络，但由几个神经粒子网络组成。尽管每个粒子网络都履行了有机体网络中单个权重的作用，但它也经过训练以自我复制自己的权重。随着有机体网络具有比简单架构的参数更多的参数，因此我们对算术任务以及简化的MNIST-DATASET分类进行了初始实验。我们观察到，单个粒子网络倾向于专注于任一任务，并且在次级任务中充分专业的粒子网络可以从网络中删除，而不会阻碍主要任务的计算准确性。这导致发现了稀疏神经网络的新颖修剪策略
We introduce organism networks, which function like a single neural network but are composed of several neural particle networks; while each particle network fulfils the role of a single weight application within the organism network, it is also trained to self-replicate its own weights. As organism networks feature vastly more parameters than simpler architectures, we perform our initial experiments on an arithmetic task as well as on simplified MNIST-dataset classification as a collective. We observe that individual particle networks tend to specialise in either of the tasks and that the ones fully specialised in the secondary task may be dropped from the network without hindering the computational accuracy of the primary task. This leads to the discovery of a novel pruning-strategy for sparse neural networks
