English
Related papers

Related papers: PURE: Turning Polysemantic Neurons Into Pure Featu…

200 papers

We study function spaces parametrized by neural networks, referred to as neuromanifolds. Specifically, we focus on deep Multi-Layer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs) with an activation function that is a…

Machine Learning · Computer Science 2026-02-16 Vahid Shahverdi , Giovanni Luca Marchetti , Kathlén Kohn

Individual neurons in neural networks often represent a mixture of unrelated features. This phenomenon, called polysemanticity, can make interpreting neural networks more difficult and so we aim to understand its causes. We propose doing so…

Neural and Evolutionary Computing · Computer Science 2025-03-26 Adam Scherlis , Kshitij Sachan , Adam S. Jermyn , Joe Benton , Buck Shlegeris

One of the biggest challenges for deep learning algorithms in medical image analysis is the indiscriminate mixing of image properties, e.g. artifacts and anatomy. These entangled image properties lead to a semantically redundant feature…

Machine Learning · Computer Science 2019-08-22 Qingjie Meng , Nick Pawlowski , Daniel Rueckert , Bernhard Kainz

Being able to interpret, or explain, the predictions made by a machine learning model is of fundamental importance. This is especially true when there is interest in deploying data-driven models to make high-stakes decisions, e.g. in…

Machine Learning · Computer Science 2019-10-01 An-phi Nguyen , María Rodríguez Martínez

To parse images into fine-grained semantic parts, the complex fine-grained elements will put it in trouble when using off-the-shelf semantic segmentation networks. In this paper, for image parsing task, we propose to parse images from…

Computer Vision and Pattern Recognition · Computer Science 2018-04-24 Jiagao Hu , Zhengxing Sun , Yunhan Sun , Jinlong Shi

Although deep neural networks have shown well-performance in various tasks, the poor interpretability of the models is always criticized. In the paper, we propose a new interpretable neural network method, by embedding neurons into the…

Machine Learning · Computer Science 2022-11-16 Wei Han , Yangqiming Wang , Christian Böhm , Junming Shao

Interpretability of deep neural networks (DNNs) is essential since it enables users to understand the overall strengths and weaknesses of the models, conveys an understanding of how the models will behave in the future, and how to diagnose…

Computer Vision and Pattern Recognition · Computer Science 2017-03-31 Yinpeng Dong , Hang Su , Jun Zhu , Bo Zhang

Deep convolutional neural networks are a powerful model class for a range of computer vision problems, but it is difficult to interpret the image filtering process they implement, given their sheer size. In this work, we introduce a method…

Computer Vision and Pattern Recognition · Computer Science 2023-04-18 Chris Hamblin , Talia Konkle , George Alvarez

In some neural networks, individual neurons correspond to natural ``features'' in the input. Such \emph{monosemantic} neurons are of great help in interpretability studies, as they can be cleanly understood. In this work we report…

Machine Learning · Computer Science 2022-11-18 Adam S. Jermyn , Nicholas Schiefer , Evan Hubinger

In this paper we introduce a new problem within the growing literature of interpretability for convolution neural networks (CNNs). While previous work has focused on the question of how to visually interpret CNNs, we ask what it is that we…

Computer Vision and Pattern Recognition · Computer Science 2022-01-03 Sílvia Casacuberta , Esra Suel , Seth Flaxman

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Patrick Esser , Robin Rombach , Björn Ommer

In this paper, we propose Describe-and-Dissect (DnD), a novel method to describe the roles of hidden neurons in vision networks. DnD utilizes recent advancements in multimodal deep learning to produce complex natural language descriptions,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-20 Nicholas Bai , Rahul A. Iyer , Tuomas Oikarinen , Akshay Kulkarni , Tsui-Wei Weng

A central goal in understanding human vision is to uncover the visual features that drive neuronal activity. A growing body of work has used artificial neural networks as encoding models to predict cortical responses to natural images,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Idan Daniel Grosbard , Mor Geva , Galit Yovel

Deep learning techniques have successfully been employed in numerous computer vision tasks including image segmentation. The techniques have also been applied to medical image segmentation, one of the most critical tasks in computer-aided…

Computer Vision and Pattern Recognition · Computer Science 2020-06-30 Titinunt Kitrungrotsakul , Iwamoto Yutaro , Lanfen Lin , Ruofeng Tong , Jingsong Li , Yen-Wei Chen

Pretrained language models (PLMs) form the basis of most state-of-the-art NLP technologies. Nevertheless, they are essentially black boxes: Humans do not have a clear understanding of what knowledge is encoded in different parts of the…

Computation and Language · Computer Science 2023-11-15 Tanja Baeumel , Soniya Vijayakumar , Josef van Genabith , Guenter Neumann , Simon Ostermann

Decoding sensory experiences from neural activity to reconstruct human-perceived visual stimuli and semantic content remains a challenge in neuroscience and artificial intelligence. Despite notable progress in current brain decoding models,…

Neurons and Cognition · Quantitative Biology 2025-10-13 Feihan Feng , Jingxin Nie

Convolutional neural network (CNN) driven by image recognition has been shown to be able to explain cortical responses to static pictures at ventral-stream areas. Here, we further showed that such CNN could reliably predict and decode…

Neurons and Cognition · Quantitative Biology 2017-11-15 Haiguang Wen , Junxing Shi , Yizhen Zhang , Kun-Han Lu , Jiayue Cao , Zhongming Liu

Deep neural networks have been widely adopted in many vision and robotics applications with visual inputs. It is essential to verify its robustness against semantic transformation perturbations, such as brightness and contrast. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Hanjiang Hu , Bowei Li , Ziwei Wang , Tianhao Wei , Casidhe Hutchison , Eric Sample , Changliu Liu

In the brain, the structure of a network of neurons defines how these neurons implement the computations that underlie the mind and the behavior of animals and humans. Provided that we can describe the network of neurons as a graph, we can…

Computer Vision and Pattern Recognition · Computer Science 2019-07-03 Gustavo Borges Moreno e Mello , Vibeke Devold Valderhaug , Sidney Pontes-Filho , Evi Zouganeli , Ioanna Sandvig , Stefano Nichele

We propose a new interpretability method for neural networks, which is based on a novel mathematico-philosophical theory of reasons. Our method computes a vector for each neuron, called its reasons vector. We then can compute how strongly…

Machine Learning · Computer Science 2025-05-21 Levin Hornischer , Hannes Leitgeb