English
Related papers

Related papers: How Important Is a Neuron?

200 papers

Deep learning has led to significant advances in artificial intelligence, in part, by adopting strategies motivated by neurophysiology. However, it is unclear whether deep learning could occur in the real brain. Here, we show that a deep…

Neurons and Cognition · Quantitative Biology 2017-04-11 Jordan Guergiuev , Timothy P. Lillicrap , Blake A. Richards

Heterogeneous network data with rich nodal information become increasingly prevalent across multidisciplinary research, yet accurately modeling complex nodal heterogeneity and simultaneously selecting influential nodal attributes remains an…

Methodology · Statistics 2026-04-14 Zhaoyu Xing , Xiufan Yu

Learning workable representations of dynamical systems is becoming an increasingly important problem in a number of application areas. By leveraging recent work connecting deep neural networks to systems of differential equations, we…

Machine Learning · Statistics 2020-03-03 Steindor Saemundsson , Alexander Terenin , Katja Hofmann , Marc Peter Deisenroth

Neural networks are becoming increasingly prevalent in software, and it is therefore important to be able to verify their behavior. Because verifying the correctness of neural networks is extremely challenging, it is common to focus on the…

Machine Learning · Computer Science 2019-02-19 Ravi Mangal , Aditya V. Nori , Alessandro Orso

It has been observed that the input space of deep neural network classifiers can exhibit `fragmentation', where the model function rapidly changes class as the input space is traversed. The severity of this fragmentation tends to follow the…

Deep learning models suffer from opaqueness. For Convolutional Neural Networks (CNNs), current research strategies for explaining models focus on the target classes within the associated training dataset. As a result, the understanding of…

Computer Vision and Pattern Recognition · Computer Science 2021-02-23 Xuehao Liu , Sarah Jane Delany , Susan McKeever

We consider causal inference in the presence of unobserved confounding. We study the case where a proxy is available for the unobserved confounding in the form of a network connecting the units. For example, the link structure of a social…

Machine Learning · Statistics 2019-06-03 Victor Veitch , Yixin Wang , David M. Blei

The widespread use of deep neural networks has achieved substantial success in many tasks. However, there still exists a huge gap between the operating mechanism of deep learning models and human-understandable decision making, so that…

Artificial Intelligence · Computer Science 2021-03-08 Xiaowei Zhou , Jie Yin , Ivor Tsang , Chen Wang

Deep learning has recently led to great successes in tasks such as image recognition (e.g Krizhevsky et al., 2012). However, deep networks are still outmatched by the power and versatility of the brain, perhaps in part due to the richer…

Machine Learning · Statistics 2014-03-25 David P. Reichert , Thomas Serre

We study characteristics of receptive fields of units in deep convolutional networks. The receptive field size is a crucial issue in many visual tasks, as the output must respond to large enough areas in the image to capture information…

Computer Vision and Pattern Recognition · Computer Science 2017-01-26 Wenjie Luo , Yujia Li , Raquel Urtasun , Richard Zemel

Complex networks are ubiquitous to several Computer Science domains. Centrality measures are an important analysis mechanism to uncover vital elements of complex networks. However, these metrics have high computational costs and…

Machine Learning · Computer Science 2018-10-30 Felipe Grando , Lisando Z. Granville , Luis C. Lamb

We derive learning rules for finding the connections between units in stochastic dynamical networks from the recorded history of a ``visible'' subset of the units. We consider two models. In both of them, the visible units are binary and…

Disordered Systems and Neural Networks · Physics 2021-04-13 Joanna Tyrcha , John Hertz

High quality explanations of neural networks (NNs) should exhibit two key properties. Completeness ensures that they accurately reflect a network's function and interpretability makes them understandable to humans. Many existing methods…

Machine Learning · Computer Science 2025-03-20 Nolan Dey , Eric Taylor , Alexander Wong , Bryan Tripp , Graham W. Taylor

Deep neural networks are widely used for classification. These deep models often suffer from a lack of interpretability -- they are particularly difficult to understand because of their non-linear nature. As a result, neural networks are…

Artificial Intelligence · Computer Science 2017-11-22 Oscar Li , Hao Liu , Chaofan Chen , Cynthia Rudin

We present a study of deep learning applied to the domain of network traffic data forecasting. This is a very important ingredient for network traffic engineering, e.g., intelligent routing, which can optimize network performance,…

Machine Learning · Computer Science 2019-09-13 Benedikt Pfülb , Christoph Hardegen , Alexander Gepperth , Sebastian Rieger

An intriguing property of deep neural networks is their inherent vulnerability to adversarial inputs, which significantly hinders their application in security-critical domains. Most existing detection methods attempt to use carefully…

Machine Learning · Computer Science 2017-12-05 Chanh Nguyen , Georgi Georgiev , Yujie Ji , Ting Wang

In linear models, visualizing a weight vector naturally reveals the model's preferred input direction, but extending this intuition to deep networks via gradients or gradient ascent often yields brittle or adversarial-looking features. We…

Machine Learning · Computer Science 2026-05-08 Maciej Satkiewicz , Roberto Corizzo , Marcin Pietroń

This paper introduces feature gradient flow, a new technique for interpreting deep learning models in terms of features that are understandable to humans. The gradient flow of a model locally defines nonlinear coordinates in the input data…

Image and Video Processing · Electrical Eng. & Systems 2023-07-26 Yinzhu Jin , Jonathan C. Garneau , P. Thomas Fletcher

Deep neural networks exhibit remarkable performance, yet their black-box nature limits their utility in fields like healthcare where interpretability is crucial. Existing explainability approaches often sacrifice accuracy and lack…

Machine Learning · Computer Science 2025-04-08 Linhui Huang , Sayeri Lala , Niraj K. Jha

Deep neural networks (DNNs) have achieved superior performance in various prediction tasks, but can be very vulnerable to adversarial examples or perturbations. Therefore, it is crucial to measure the sensitivity of DNNs to various forms of…

Machine Learning · Statistics 2019-12-23 Hai Shu , Hongtu Zhu