Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applications

• URL: http://arxiv.org/abs/2302.01440v1
• Date: Thu, 2 Feb 2023 22:02:33 GMT
• Title: Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applications
• Authors: Chengyu Dong
• Abstract summary: We show that the uncertainty of deep neural networks is not only important in a sense of interpretability and transparency, but also crucial in further advancing their performance. We will generalize the definition of the uncertainty of deep neural networks to any number or vector that is associated with an input or an input-label pair, and catalog existing methods on mining'' such uncertainty from a deep model.
• Score: 1.9671123873378717
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks have seen enormous success in various real-world applications. Beyond their predictions as point estimates, increasing attention has been focused on quantifying the uncertainty of their predictions. In this review, we show that the uncertainty of deep neural networks is not only important in a sense of interpretability and transparency, but also crucial in further advancing their performance, particularly in learning systems seeking robustness and efficiency. We will generalize the definition of the uncertainty of deep neural networks to any number or vector that is associated with an input or an input-label pair, and catalog existing methods on ``mining'' such uncertainty from a deep model. We will include those methods from the classic field of uncertainty quantification as well as those methods that are specific to deep neural networks. We then show a wide spectrum of applications of such generalized uncertainty in realistic learning tasks including robust learning such as noisy learning, adversarially robust learning; data-efficient learning such as semi-supervised and weakly-supervised learning; and model-efficient learning such as model compression and knowledge distillation.

Related papers

• Computability of Classification and Deep Learning: From Theoretical Limits to Practical Feasibility through Quantization [53.15874572081944]
  We study computability in the deep learning framework from two perspectives. We show algorithmic limitations in training deep neural networks even in cases where the underlying problem is well-behaved. Finally, we show that in quantized versions of classification and deep network training, computability restrictions do not arise or can be overcome to a certain degree.
  arXiv  Detail & Related papers  (2024-08-12T15:02:26Z)
• Coding schemes in neural networks learning classification tasks [52.22978725954347]
  We investigate fully-connected, wide neural networks learning classification tasks. We show that the networks acquire strong, data-dependent features. Surprisingly, the nature of the internal representations depends crucially on the neuronal nonlinearity.
  arXiv  Detail & Related papers  (2024-06-24T14:50:05Z)
• The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning [73.5095051707364]
  We consider classical distribution-agnostic framework and algorithms minimising empirical risks. We show that there is a large family of tasks for which computing and verifying ideal stable and accurate neural networks is extremely challenging.
  arXiv  Detail & Related papers  (2023-09-13T16:33:27Z)
• Uncertainty Estimation by Fisher Information-based Evidential Deep Learning [61.94125052118442]
  Uncertainty estimation is a key factor that makes deep learning reliable in practical applications. We propose a novel method, Fisher Information-based Evidential Deep Learning ($mathcalI$-EDL) In particular, we introduce Fisher Information Matrix (FIM) to measure the informativeness of evidence carried by each sample, according to which we can dynamically reweight the objective loss terms to make the network more focused on the representation learning of uncertain classes.
  arXiv  Detail & Related papers  (2023-03-03T16:12:59Z)
• Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction [50.79827516897913]
  We introduce an interpretable paradigm for trajectory prediction that distributes the uncertainty among semantic concepts. We validate our approach on real-world autonomous driving data, demonstrating superior performance over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-11-16T06:28:20Z)
• Uncertainty Quantification and Resource-Demanding Computer Vision Applications of Deep Learning [5.130440339897478]
  Bringing deep neural networks (DNNs) into safety critical applications requires a thorough treatment of the model's uncertainties. In this article, we survey methods that we developed to teach DNNs to be uncertain when they encounter new object classes. We also present training methods to learn from only a few labels with help of uncertainty quantification.
  arXiv  Detail & Related papers  (2022-05-30T08:31:03Z)
• Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration [12.05471394131891]
  We provide a new framework for sparse deep learning, which has the above issues addressed in a coherent way. We lay down a theoretical foundation for sparse deep learning and propose prior annealing algorithms for learning sparse neural networks.
  arXiv  Detail & Related papers  (2021-10-01T21:16:34Z)
• A Survey of Uncertainty in Deep Neural Networks [39.68313590688467]
  It is intended to give anyone interested in uncertainty estimation in neural networks a broad overview and introduction. A comprehensive introduction to the most crucial sources of uncertainty is given and their separation into reducible model uncertainty and not reducible data uncertainty is presented. For a practical application, we discuss different measures of uncertainty, approaches for the calibration of neural networks and give an overview of existing baselines and implementations.
  arXiv  Detail & Related papers  (2021-07-07T16:39:28Z)
• A neural anisotropic view of underspecification in deep learning [60.119023683371736]
  We show that the way neural networks handle the underspecification of problems is highly dependent on the data representation. Our results highlight that understanding the architectural inductive bias in deep learning is fundamental to address the fairness, robustness, and generalization of these systems.
  arXiv  Detail & Related papers  (2021-04-29T14:31:09Z)
• Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users [27.764388500937983]
  Bayesian statistics offer a formalism to understand and quantify the uncertainty associated with deep neural network predictions. This tutorial provides an overview of the relevant literature and a complete toolset to design, implement train, use and evaluate Bayesian Neural Networks.
  arXiv  Detail & Related papers  (2020-07-14T05:21:27Z)
• Bayesian Neural Networks [0.0]
  We show how errors in prediction by neural networks can be obtained in principle, and provide the two favoured methods for characterising these errors. We will also describe how both of these methods have substantial pitfalls when put into practice.
  arXiv  Detail & Related papers  (2020-06-02T09:43:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.