Invariance has recently proven to be a powerful inductive bias in machine learning models. One such class of predictive or generative models are tensor networks. We introduce a new numerical algorithm to construct a basis of tensors that are invariant under the action of normal matrix representations of an arbitrary discrete group. This method can be up to several orders of magnitude faster than previous approaches. The group-invariant tensors are then combined into a group-invariant tensor train network, which can be used as a supervised machine learning model. We applied this model to a protein binding classification problem, taking into account problem-specific invariances, and obtained prediction accuracy in line with state-of-the-art deep learning approaches.

翻译：最近,在机器学习模型中,惯性被证明是强烈的感性偏差。一类预测或基因模型是高频网络。我们引入了一种新的数字算法,在任意的离散群体正常矩阵表达法的操作下,构建一个无变数的数组基础。这种方法可能比以前的方法快到几个数量级。组变数数组随后被合并成一个群变数的数组火车网络,可以用作监督的机器学习模型。我们将这一模型应用于蛋白质约束性分类问题,同时考虑到特定问题的变异,并获得了符合最新深层学习方法的预测准确性。