0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 3 years have passed since last update.

Deep Evidential Regression【Abstract】【論文 DeepL 翻訳】

Last updated at Posted at 2020-12-09

この記事は自分用のメモみたいなものです.
ほぼ DeepL 翻訳でお送りします.
間違いがあれば指摘していだだけると嬉しいです.

翻訳元
Deep Evidential Regression
Author: Alexander Amini, Wilko Schwarting, Ava Soleimany, Daniela Rus

前: 無し
次: 【1 Introduction】

Abstract

訳文

決定論的ニューラルネットワーク (NNs) は, 不確実性の校正された, ロバストで効率的な測定が重要である安全上重要な領域において, ますます導入が進んでいる. 本論文では, 非ベイズ型 NNs を学習するための新しい方法を提案し, 連続的なターゲットとそれに関連する証拠を推定する. これは, 元のガウス尤度関数に証拠的な事前分布を置き, NN を訓練して証拠分布のハイパーパラメタを推論することによって達成される. さらに, 予測された証拠が正しい出力と一致していない場合, モデルが正則化されるように訓練中に priors を課す. 我々の方法は, 推論中のサンプリングや, 訓練のための分布外 (OOD) 例に依存しないため, 効率的でスケーラブルな不確実性学習を可能にする. 我々は, 様々なベンチマーク上で較正された不確実性の尺度を学習し, 複雑なコンピュータビジョンタスクへのスケーリングを実証し, 敵対的や OOD テストサンプルへのロバスト性も実証している.

原文

Deterministic neural networks (NNs) are increasingly being deployed in safety critical domains, where calibrated, robust, and efficient measures of uncertainty are crucial. In this paper, we propose a novel method for training non-Bayesian NNs to estimate a continuous target as well as its associated evidence in order to learn both aleatoric and epistemic uncertainty. We accomplish this by placing evidential priors over the original Gaussian likelihood function and training the NN to infer the hyperparameters of the evidential distribution. We additionally impose priors during training such that the model is regularized when its predicted evidence is not aligned with the correct output. Our method does not rely on sampling during inference or on out-of-distribution (OOD) examples for training, thus enabling efficient and scalable uncertainty learning. We demonstrate learning well-calibrated measures of uncertainty on various benchmarks, scaling to complex computer vision tasks, as well as robustness to adversarial and OOD test samples.

0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?