论文标题
有限状态概率RNN的不确定性估计和校准
Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNs
论文作者
论文摘要
不确定性量化对于构建可靠且可信赖的机器学习系统至关重要。我们建议通过随机离散状态过渡对复发时间段的转变来估计复发性神经网络（RNN）的不确定性。可以通过多次运行预测来量化模型的不确定性，每次从复发状态过渡分布进行采样，如果模型不确定，则可能会导致可能不同的结果。除了不确定性量化外，我们提出的方法在不同的环境中提供了几个优势。提出的方法可以（1）从数据中学习确定性和概率自动机，（2）在现实世界分类任务上学习良好的模型，（3）提高分布外检测的性能，（4）控制探索 - 探索在强化学习中的折算。
Uncertainty quantification is crucial for building reliable and trustable machine learning systems. We propose to estimate uncertainty in recurrent neural networks (RNNs) via stochastic discrete state transitions over recurrent timesteps. The uncertainty of the model can be quantified by running a prediction several times, each time sampling from the recurrent state transition distribution, leading to potentially different results if the model is uncertain. Alongside uncertainty quantification, our proposed method offers several advantages in different settings. The proposed method can (1) learn deterministic and probabilistic automata from data, (2) learn well-calibrated models on real-world classification tasks, (3) improve the performance of out-of-distribution detection, and (4) control the exploration-exploitation trade-off in reinforcement learning.
