ベイズ最適化とラプラス近似によるロボットの自己認識
Bayesian Optimization Meets Laplace Approximation for Robotic Introspection
深層ニューラルネットワークの不確実性推定を改善するため、ラプラス近似の過小適合を緩和するベイズ最適化手法を提案し、予測の校正と精度を同時に最適化できることを示した。
著者: Matthias Humt, Jongseok Lee, Rudolph Triebel
分類: cs.RO, cs.CV, cs.LG
原文アブストラクト
In robotics, deep learning (DL) methods are used more and more widely, but their general inability to provide reliable confidence estimates will ultimately lead to fragile and unreliable systems. This impedes the potential deployments of DL methods for long-term autonomy. Therefore, in this paper we introduce a scalable Laplace Approximation (LA) technique to make Deep Neural Networks (DNNs) more introspective, i.e. to enable them to provide accurate assessments of their failure probability for unseen test data. In particular, we propose a novel Bayesian Optimization (BO) algorithm to mitigate their tendency of under-fitting the true weight posterior, so that both the calibration and the accuracy of the predictions can be simultaneously optimized. We demonstrate empirically that the proposed BO approach requires fewer iterations for this when compared to random search, and we show that the proposed framework can be scaled up to large datasets and architectures.
