English
Related papers

Related papers: The (Un)reliability of saliency methods

200 papers

Machine learning methods can be unreliable when deployed in domains that differ from the domains on which they were trained. There are a wide range of proposals for mitigating this problem by learning representations that are ``invariant''…

Machine Learning · Statistics 2023-02-09 Zihao Wang , Victor Veitch

In this paper, we introduce a strategy for identifying textual saliency in large-scale language models applied to classification tasks. In visual networks where saliency is more well-studied, saliency is naturally localized through the…

Computation and Language · Computer Science 2023-08-11 Elizabeth M. Hou , Gregory Castanon

Explainability is needed to establish confidence in machine learning results. Some explainable methods take a post hoc approach to explain the weights of machine learning models, others highlight areas of the input contributing to…

Machine Learning · Computer Science 2024-07-15 Paul Whitten , Francis Wolff , Chris Papachristou

We study the problem of attributing the prediction of a deep network to its input features, a problem previously studied by several other works. We identify two fundamental axioms---Sensitivity and Implementation Invariance that attribution…

Machine Learning · Computer Science 2017-06-14 Mukund Sundararajan , Ankur Taly , Qiqi Yan

In recent years, considerable work has been devoted to explaining predictive, deep learning-based models, and in turn how to evaluate explanations. An important class of evaluation methods are ones that are human-centered, which typically…

Computer Vision and Pattern Recognition · Computer Science 2024-06-13 Yayan Zhao , Mingwei Li , Matthew Berger

Causal inference is capable of estimating the treatment effect (i.e., the causal effect of treatment on the outcome) to benefit the decision making in various domains. One fundamental challenge in this research is that the treatment…

Machine Learning · Computer Science 2021-12-28 Qian Li , Zhichao Wang , Shaowu Liu , Gang Li , Guandong Xu

The computation and memory needed for Convolutional Neural Network (CNN) inference can be reduced by pruning weights from the trained network. Pruning is guided by a pruning saliency, which heuristically approximates the change in the loss…

Computer Vision and Pattern Recognition · Computer Science 2021-06-25 Kaveena Persand , Andrew Anderson , David Gregg

Variational Bayesian posterior inference often requires simplifying approximations such as mean-field parametrisation to ensure tractability. However, prior work has associated the variational mean-field approximation for Bayesian neural…

Machine Learning · Computer Science 2022-10-07 Richard Kurle , Ralf Herbrich , Tim Januschowski , Yuyang Wang , Jan Gasthaus

It is often said that a deep learning model is "invariant" to some specific type of transformation. However, what is meant by this statement strongly depends on the context in which it is made. In this paper we explore the nature of…

Machine Learning · Computer Science 2022-10-11 Henry Kvinge , Tegan H. Emerson , Grayson Jorgenson , Scott Vasquez , Timothy Doster , Jesse D. Lew

The fundamental challenge of drawing causal inference is that counterfactual outcomes are not fully observed for any unit. Furthermore, in observational studies, treatment assignment is likely to be confounded. Many statistical methods have…

Methodology · Statistics 2022-08-01 Harsh Parikh , Carlos Varjao , Louise Xu , Eric Tchetgen Tchetgen

Methods for understanding the decisions of and mechanisms underlying deep neural networks (DNNs) typically rely on building intuition by emphasizing sensory or semantic features of individual examples. For instance, methods aim to visualize…

Computers and Society · Computer Science 2020-10-26 Matthew L. Leavitt , Ari Morcos

Explaining predictions based on multivariate time series data carries the additional difficulty of handling not only multiple features, but also time dependencies. It matters not only what happened, but also when, and the same feature could…

Machine Learning · Computer Science 2023-05-31 Joseph Enguehard

The willingness to trust predictions formulated by automatic algorithms is key in a vast number of domains. However, a vast number of deep architectures are only able to formulate predictions without an associated uncertainty. In this…

Image and Video Processing · Electrical Eng. & Systems 2022-09-28 Matteo Ferrante , Tommaso Boccato , Nicola Toschi

The different families of saliency methods, either based on contrastive signals, closed-form formulas mixing gradients with activations or on perturbation masks, all focus on which parts of an image are responsible for the model's…

Computer Vision and Pattern Recognition · Computer Science 2019-10-22 Sylvestre-Alvise Rebuffi , Ruth Fong , Xu Ji , Hakan Bilen , Andrea Vedaldi

The inability of artificial neural networks to assess the uncertainty of their predictions is an impediment to their widespread use. We distinguish two types of learnable uncertainty: model uncertainty due to a lack of training data and…

Machine Learning · Computer Science 2022-06-14 Hans Weytjens , Jochen De Weerdt

Convolutional neural networks (CNNs) offer great machine learning performance over a range of applications, but their operation is hard to interpret, even for experts. Various explanation algorithms have been proposed to address this issue,…

Human-Computer Interaction · Computer Science 2020-02-04 Ahmed Alqaraawi , Martin Schuessler , Philipp Weiß , Enrico Costanza , Nadia Berthouze

Understanding the uncertainty of a neural network's (NN) predictions is essential for many purposes. The Bayesian framework provides a principled approach to this, however applying it to NNs is challenging due to large numbers of parameters…

Machine Learning · Statistics 2020-02-27 Tim Pearce , Felix Leibfried , Alexandra Brintrup , Mohamed Zaki , Andy Neely

Deep saliency prediction algorithms complement the object recognition features, they typically rely on additional information, such as scene context, semantic relationships, gaze direction, and object dissimilarity. However, none of these…

Computer Vision and Pattern Recognition · Computer Science 2024-09-11 Bahar Aydemir , Ludo Hoffstetter , Tong Zhang , Mathieu Salzmann , Sabine Süsstrunk

Uncertainty is a key feature of any machine learning model and is particularly important in neural networks, which tend to be overconfident. This overconfidence is worrying under distribution shifts, where the model performance silently…

Machine Learning · Computer Science 2024-03-18 Arthur Thuy , Dries F. Benoit

We present a novel approach for training deep neural networks in a Bayesian way. Classical, i.e. non-Bayesian, deep learning has two major drawbacks both originating from the fact that network parameters are considered to be deterministic.…

Machine Learning · Statistics 2019-03-11 Konstantin Posch , Jan Steinbrener , Jürgen Pilz
‹ Prev 1 4 5 6 7 8 10 Next ›