English
Related papers

Related papers: Gradient-based Analysis of NLP Models is Manipulab…

200 papers

Recent developments in machine learning have introduced models that approach human performance at the cost of increased architectural complexity. Efforts to make the rationales behind the models' predictions transparent have inspired an…

Computation and Language · Computer Science 2020-09-29 Pepa Atanasova , Jakob Grue Simonsen , Christina Lioma , Isabelle Augenstein

Saliency maps are a popular approach for explaining classifications of (convolutional) neural networks. However, it remains an open question as to how best to evaluate salience maps, with three families of evaluation methods commonly being…

Human-Computer Interaction · Computer Science 2025-04-25 Felix Kares , Timo Speith , Hanwei Zhang , Markus Langer

It is known that deep neural networks (DNNs) classify an input image by paying particular attention to certain specific pixels; a graphical representation of the magnitude of attention to each pixel is called a saliency-map. Saliency-maps…

Computer Vision and Pattern Recognition · Computer Science 2022-07-14 Satoshi Munakata , Caterina Urban , Haruki Yokoyama , Koji Yamamoto , Kazuki Munakata

In the past decade gradient-based deep learning has revolutionized several applications. However, this rapid advancement has highlighted the need for a deeper theoretical understanding of its limitations. Research has shown that, in many…

Machine Learning · Computer Science 2025-05-30 Rustem Takhanov

When do gradient-based explanation algorithms provide perceptually-aligned explanations? We propose a criterion: the feature attributions need to be aligned with the tangent space of the data manifold. To provide evidence for this…

Machine Learning · Computer Science 2024-07-16 Sebastian Bordt , Uddeshya Upadhyay , Zeynep Akata , Ulrike von Luxburg

One of the remarkable properties of robust computer vision models is that their input-gradients are often aligned with human perception, referred to in the literature as perceptually-aligned gradients (PAGs). Despite only being trained for…

Machine Learning · Computer Science 2024-03-12 Suraj Srinivas , Sebastian Bordt , Hima Lakkaraju

Saliency methods aim to explain the predictions of deep neural networks. These methods lack reliability when the explanation is sensitive to factors that do not contribute to the model prediction. We use a simple and common pre-processing…

Machine learning (ML) model explainability has received growing attention, especially in the area related to model risk and regulations. In this paper, we reviewed and compared some popular ML model explainability methodologies, especially…

Artificial Intelligence · Computer Science 2021-06-15 Shafie Gholizadeh , Nengfeng Zhou

Projected Gradient Descent denotes a class of iterative methods for solving optimization programs. Its applicability to convex optimization programs has gained significant popularity for its intuitive implementation that involves only…

Optimization and Control · Mathematics 2016-10-24 Giampaolo Torrisi , Sergio Grammatico , Roy S. Smith , Manfred Morari

Explanation methods aim to make neural networks more trustworthy and interpretable. In this paper, we demonstrate a property of explanation methods which is disconcerting for both of these purposes. Namely, we show that explanations can be…

Integrating heterogeneous biomedical data including imaging, omics, and clinical records supports accurate diagnosis and personalised care. Graph-based models fuse such non-Euclidean data by capturing spatial and relational structure, yet…

Genomics · Quantitative Biology 2025-05-06 Alireza Sadeghi , Farshid Hajati , Ahmadreza Argha , Nigel H Lovell , Min Yang , Hamid Alinejad-Rokny

Designing models that produce accurate predictions is the fundamental objective of machine learning (ML). This work presents methods demonstrating that when the derivatives of target variables (outputs) with respect to inputs can be…

Machine Learning · Computer Science 2022-01-17 Chris McDonagh , Xi Chen

Adversarially robust classifiers possess a trait that non-robust models do not -- Perceptually Aligned Gradients (PAG). Their gradients with respect to the input align well with human perception. Several works have identified PAG as a…

Computer Vision and Pattern Recognition · Computer Science 2023-08-10 Roy Ganz , Bahjat Kawar , Michael Elad

Linear layers in neural networks (NNs) trained by gradient descent can be expressed as a key-value memory system which stores all training datapoints and the initial weights, and produces outputs using unnormalised dot attention over the…

Machine Learning · Computer Science 2022-06-20 Kazuki Irie , Róbert Csordás , Jürgen Schmidhuber

Deep neural networks are known to be vulnerable to adversarial perturbations, which are small and carefully crafted inputs that lead to incorrect predictions. In this paper, we propose DeepDefense, a novel defense framework that applies…

Machine Learning · Computer Science 2025-11-19 Ci Lin , Tet Yeap , Iluju Kiringa , Biwei Zhang

In recent years, Deep Learning has become the go-to solution for a broad range of applications, often outperforming state-of-the-art. However, it is important, for both theoreticians and practitioners, to gain a deeper understanding of the…

Machine Learning · Computer Science 2017-04-28 Shai Shalev-Shwartz , Ohad Shamir , Shaked Shammah

We propose a categorical semantics of gradient-based machine learning algorithms in terms of lenses, parametrised maps, and reverse derivative categories. This foundation provides a powerful explanatory and unifying framework: it…

Machine Learning · Computer Science 2021-07-14 G. S. H. Cruttwell , Bruno Gavranović , Neil Ghani , Paul Wilson , Fabio Zanasi

Deep neural networks achieve state-of-the-art and sometimes super-human performance across various domains. However, when learning tasks sequentially, the networks easily forget the knowledge of previous tasks, known as "catastrophic…

Computer Vision and Pattern Recognition · Computer Science 2021-05-18 Shixiang Tang , Dapeng Chen , Jinguo Zhu , Shijie Yu , Wanli Ouyang

The idea of federated learning is to collaboratively train a neural network on a server. Each user receives the current weights of the network and in turns sends parameter updates (gradients) based on local data. This protocol has been…

Computer Vision and Pattern Recognition · Computer Science 2020-09-14 Jonas Geiping , Hartmut Bauermeister , Hannah Dröge , Michael Moeller

The empirical success of derivative-free methods in reinforcement learning for planning through contact seems at odds with the perceived fragility of classical gradient-based optimization methods in these domains. What is causing this gap,…

Robotics · Computer Science 2022-01-25 H. J. Terry Suh , Tao Pang , Russ Tedrake
‹ Prev 1 8 9 10 Next ›