arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.03626cs.LGcs.NE
收藏

极值学习:在回归问题中极值化神经网络的输出

Extremal learning: extremizing the output of a neural network in regression problems

McMaster University(麦克马斯特大学);AI Endurance Inc(AI Endurance公司)

Zakaria Patel, Markus Rummel

摘要:

神经网络允许我们对变量之间的复杂关系进行建模。我们展示了如何有效地找到极值的训练神经网络回归问题。找到近似模型的极值输入被公式化为训练具有当达到极值输入时最小化的损失函数的附加神经网络。我们进一步展示了如何将额外的限制输入向量,如限制外推的极值输入向量从原始的训练数据集。包含使用TensorFlow的这种方法的教学示例。

英文摘要:

Neural networks allow us to model complex relationships between variables. We show how to efficiently find extrema of a trained neural network in regression problems. Finding the extremizing input of an approximated model is formulated as the training of an additional neural network with a loss function that minimizes when the extremizing input is achieved. We further show how to incorporate additional constraints on the input vector such as limiting the extrapolation of the extremizing input vector from the original training data set. An instructional example of this approach using TensorFlow is included.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑