Pruning coupled with learning aims to optimize the neural network (NN) structure for solving specific problems. This optimization can be used for various purposes: to prevent overfitting, to save resources for implementation and training, to provide explainability of the trained NN, and many others. The minimal structure that cannot be pruned further is not unique. Ensemble of minimal structures can be used as a committee of intellectual agents that solves problems by voting. Each minimal NN presents an "empirical knowledge" about the problem and can be verbalized. The non-uniqueness of such knowledge extracted from data is an important property of data-driven Artificial Intelligence (AI). In this work, we review an approach to pruning based on the principle: What controls training should control pruning. This principle is expected to work both for artificial NN and for selection and modification of important synaptic contacts in brain. In back-propagation artificial NN learning is controlled by the gradient of loss functions. Therefore, the first order sensitivity indicators are used for pruning and the algorithms based on these indicators are reviewed. The notion of logically transparent NN was introduced. The approach was illustrated on the problem of political forecasting: predicting the results of the US presidential election. Eight minimal NN were produced that give different forecasting algorithms. The non-uniqueness of solution can be utilised by creation of expert panels (committee). Another use of NN pluralism is to identify areas of input signals where further data collection is most useful. In Conclusion, we discuss the possible future of widely advertised XAI program.
翻译:与学习结合, 目的是优化神经网络( NN) 结构, 以解决具体问题。 这种优化可以用于各种目的: 防止过度配置, 节省用于执行和培训的资源, 提供受过训练的NNN 和其他许多项目的可解释性。 无法进一步调整的最低限度结构并不独特。 最小结构的集合可以用作知识分子委员会, 通过投票解决问题。 最小的NNN 提供了对问题的“ 经验性知识”, 可以言语化。 从数据中提取的这种知识的非独特性是数据驱动的人工智能(AI)的重要属性。 在这项工作中, 我们根据原则来审查剪裁的方法: 哪些控制培训应该控制剪裁。 这一原则预期会同时用于人为NNW, 选择和修改大脑中重要的合成接触。 在对 NNN 的反演练中, 由损失函数的渐渐渐变功能来控制。 因此, 从数据转换出来的第一级敏感度指标被广泛用于运行, 而基于这些指标的算法是一个重要的属性。 在这项工作中, 最具有逻辑性的透明度的 Rassionalal 。 的 Ralalalalalalalalbisal is is the the the ex ex ex laviewd the laview the the liview sal rodudududududududududududududing the the the the the the s plemental plemental plemental plemental pal plemental pal pal rodududududing limental limentaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldmentaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldal rodaldaldaldaldaldaldaldaldaldaldaldaldal robaldal roal roal rodal rodal rodal rodaldaldaldal rodaldaldaldaldaldald roisal rodal rodalalal