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

翻译：我们引入了有机体网络，其功能类似于单个神经网络，但由多个神经粒子网络组成；每个粒子网络在有机体网络中扮演单次权重应用的角色，同时被训练以自复制其自身的权重。由于有机体网络的参数量远超简单架构，我们首先在算术任务以及简化的MNIST数据集分类任务上以集体方式进行了初步实验。我们观察到，单个粒子网络倾向于专项化于其中一项任务，而完全专项化于次要任务的粒子网络可以从网络中移除，而不会影响主要任务的计算精度。这一发现揭示了一种针对稀疏神经网络的新型剪枝策略。