English
Related papers

Related papers: Towards Combinatorial Interpretability of Neural C…

200 papers

Binary code similarity detection is a core task in reverse engineering. It supports malware analysis and vulnerability discovery by identifying semantically similar code in different contexts. Modern methods have progressed from manually…

Artificial Intelligence · Computer Science 2025-09-30 Charles E. Gagnon , Steven H. H. Ding , Philippe Charland , Benjamin C. M. Fung

In parallel with the success of CNNs to solve vision problems, there is a growing interest in developing methodologies to understand and visualize the internal representations of these networks. How the responses of a trained CNN encode the…

Computer Vision and Pattern Recognition · Computer Science 2015-11-18 Ivet Rafegas , Maria Vanrell

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

Convolutional neural networks (CNNs) have achieved astonishing performance on various image classification tasks, but it is difficult for humans to understand how a classification comes about. Recent literature proposes methods to explain…

Computer Vision and Pattern Recognition · Computer Science 2021-09-21 Anna Nguyen , Daniel Hagenmayer , Tobias Weller , Michael Färber

Photonic Neural Networks (PNNs) are gaining significant interest in the research community due to their potential for high parallelization, low latency, and energy efficiency. PNNs compute using light, which leads to several differences in…

Convolutional neural networks (CNN) are known to learn an image representation that captures concepts relevant to the task, but do so in an implicit way that hampers model interpretability. However, one could argue that such a…

Computer Vision and Pattern Recognition · Computer Science 2020-09-21 Diego Marcos , Ruth Fong , Sylvain Lobry , Remi Flamary , Nicolas Courty , Devis Tuia

An important line of research attempts to explain CNN image classifier predictions and intermediate layer representations in terms of human-understandable concepts. Previous work supports that deep representations are linearly separable…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Alexandros Doumanoglou , Stylianos Asteriadis , Dimitrios Zarpalas

What does a neural network encode about a concept as we traverse through the layers? Interpretability in machine learning is undoubtedly important, but the calculations of neural networks are very challenging to understand. Attempts to see…

Machine Learning · Computer Science 2020-12-14 Zhi Chen , Yijie Bei , Cynthia Rudin

While many recent methods aim to unlearn or remove knowledge from pretrained models, seemingly erased knowledge often persists and can be recovered in various ways. Because large foundation models are far from interpretable, understanding…

Machine Learning · Computer Science 2026-02-24 Shingo Kodama , Niv Cohen , Micah Adler , Nir Shavit

Linear models are widely used in computational neuroimaging to identify biomarkers associated with brain pathologies. However, interpreting the learned weights remains challenging, as they do not always yield clinically meaningful insights.…

Machine Learning · Computer Science 2026-04-23 Sara Petiton , Antoine Grigis , Raphaël Vock , Edouard Duchesnay

When neural networks are trained to classify a dataset, one finds a set of weights from which the network produces a label for each data point. We study the algorithmic complexity of finding a collision in a single-layer neural net, where a…

Predictive coding is a message-passing framework initially developed to model information processing in the brain, and now also topic of research in machine learning due to some interesting properties. One of such properties is the natural…

Machine Learning · Computer Science 2022-12-12 Billy Byiringiro , Tommaso Salvatori , Thomas Lukasiewicz

Deep convolutional neural networks (CNNs) have been successful in many tasks in machine vision, however, millions of weights in the form of thousands of convolutional filters in CNNs makes them difficult for human intepretation or…

Computer Vision and Pattern Recognition · Computer Science 2020-03-26 Reza Abbasi-Asl , Bin Yu

The purpose of feature extraction on convolutional neural networks is to reuse deep representations learnt for a pre-trained model to solve a new, potentially unrelated problem. However, raw feature extraction from all layers is unfeasible…

Neural and Evolutionary Computing · Computer Science 2019-11-11 Victor Gimenez-Abalos , Armand Vilalta , Dario Garcia-Gasulla , Jesus Labarta , Eduard Ayguadé

We propose a compact and effective framework to fuse multimodal features at multiple layers in a single network. The framework consists of two innovative fusion schemes. Firstly, unlike existing multimodal methods that necessitate…

Computer Vision and Pattern Recognition · Computer Science 2021-08-12 Yikai Wang , Fuchun Sun , Ming Lu , Anbang Yao

One of the roadblocks to a better understanding of neural networks' internals is \textit{polysemanticity}, where neurons appear to activate in multiple, semantically distinct contexts. Polysemanticity prevents us from identifying concise,…

Machine Learning · Computer Science 2023-10-05 Hoagy Cunningham , Aidan Ewart , Logan Riggs , Robert Huben , Lee Sharkey

Specifying a computational problem requires fixing encodings for input and output: encoding graphs as adjacency matrices, characters as integers, integers as bit strings, and vice versa. For such discrete data, the actual encoding is…

Logic · Mathematics 2021-08-25 Donghyun Lim , Martin Ziegler

Convolutional networks are ubiquitous in deep learning. They are particularly useful for images, as they reduce the number of parameters, reduce training time, and increase accuracy. However, as a model of the brain they are seriously…

Machine Learning · Computer Science 2022-01-19 Roman Pogodin , Yash Mehta , Timothy P. Lillicrap , Peter E. Latham

Neural networks are powerful tools for cognitive modeling due to their flexibility and emergent properties. However, interpreting their learned representations remains challenging due to their sub-symbolic semantics. In this work, we…

Machine Learning · Computer Science 2026-04-07 Andrew Nam , Declan Campbell , Thomas Griffiths , Jonathan Cohen , Sarah-Jane Leslie

Convolutional neural networks have been successfully applied to various NLP tasks. However, it is not obvious whether they model different linguistic patterns such as negation, intensification, and clause compositionality to help the…

Computation and Language · Computer Science 2018-10-23 Mahnaz Koupaee , William Yang Wang