English
Related papers

Related papers: From Data Statistics to Feature Geometry: How Corr…

200 papers

Neural networks represent more features than they have dimensions via superposition, forcing features to share representational space. Current methods decompose activations into sparse linear features but discard geometric structure. We…

Machine Learning · Computer Science 2026-02-03 Georgi Ivanov , Narmeen Oozeer , Shivam Raval , Tasana Pejovic , Shriyash Upadhyay , Amir Abdullah

Comparing the internal representations of neural networks is a central goal in both neuroscience and machine learning. Standard alignment metrics operate on raw neural activations, implicitly assuming that similar representations produce…

Machine Learning · Computer Science 2026-04-02 Sunny Liu , Habon Issa , André Longon , Liv Gorton , Meenakshi Khosla , David Klindt

Understanding how information is represented in neural networks is a fundamental challenge in both neuroscience and artificial intelligence. Despite their nonlinear architectures, recent evidence suggests that neural networks encode…

Machine Learning · Computer Science 2025-03-04 David Klindt , Charles O'Neill , Patrik Reizinger , Harald Maurer , Nina Miolane

Superposition or Neuron Polysemanticity are important concepts in the field of interpretability and one might say they are these most intricately beautiful blockers in our path of decoding the Machine Learning black-box. The idea behind…

Machine Learning · Computer Science 2024-12-24 Akanksha Devkar

The Bag-of-Words (BoW) representation is well applied to recent state-of-the-art image retrieval works. Typically, multiple vocabularies are generated to correct quantization artifacts and improve recall. However, this routine is corrupted…

Computer Vision and Pattern Recognition · Computer Science 2014-04-15 Liang Zheng , Shengjin Wang , Wengang Zhou , Qi Tian

Superposition, the ability of neural networks to represent more features than neurons, is increasingly seen as key to the efficiency of large models. This paper investigates the theoretical foundations of computing in superposition,…

Computational Complexity · Computer Science 2026-02-27 Micah Adler , Nir Shavit

Superposition refers to encoding representations of multiple features within a single neuron, which is common in deep neural networks. This property allows neurons to combine and represent multiple features, enabling the model to capture…

Machine Learning · Computer Science 2025-02-12 Ruidi Chang , Chunyuan Deng , Hanjie Chen

High-dimensional representations for words, text, images, knowledge graphs and other structured data are commonly used in different paradigms of machine learning and data mining. These representations have different degrees of…

Computation and Language · Computer Science 2020-11-26 Sunipa Dev

Interpreting graph neural networks (GNNs) is difficult because message passing mixes signals and internal channels rarely align with human concepts. We study superposition, the sharing of directions by multiple features, directly in the…

Machine Learning · Computer Science 2026-01-19 Lukas Pertl , Han Xuanyuan , Pietro Liò

The superposition hypothesis states that single neurons may participate in representing multiple features in order for the neural network to represent more features than it has neurons. In neuroscience and AI, representational alignment…

Machine Learning · Computer Science 2025-11-14 André Longon , David Klindt , Meenakshi Khosla

Machine learning model bias can arise from dataset composition: correlated sensitive features can distort the downstream classification model's decision boundary and lead to performance differences along these features. Existing de-biasing…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Miao Zhang , Zee fryer , Ben Colman , Ali Shahriyari , Gaurav Bharaj

Superposition -- when a neural network represents more ``features'' than it has dimensions -- seems to pose a serious challenge to mechanistically interpreting current AI systems. Existing theory work studies \emph{representational}…

Machine Learning · Computer Science 2024-08-13 Kaarel Hänni , Jake Mendel , Dmitry Vaintrob , Lawrence Chan

A longstanding question in cognitive science concerns the learning mechanisms underlying compositionality in human cognition. Humans can infer the structured relationships (e.g., grammatical rules) implicit in their sensory observations…

Machine Learning · Computer Science 2021-05-20 Jacob Russin , Roland Fernandez , Hamid Palangi , Eric Rosen , Nebojsa Jojic , Paul Smolensky , Jianfeng Gao

Words in some natural languages can have a composite structure. Elements of this structure include the root (that could also be composite), prefixes and suffixes with which various nuances and relations to other words can be expressed.…

Computation and Language · Computer Science 2017-09-05 Rustem Takhanov , Zhenisbek Assylbekov

Feature-based format is the main data representation format used by machine learning algorithms. When the features do not properly describe the initial data, performance starts to degrade. Some algorithms address this problem by internally…

Artificial Intelligence · Computer Science 2015-12-18 Marian-Andrei Rizoiu , Julien Velcin , Stéphane Lallich

Adversarial examples -- inputs with imperceptible perturbations that fool neural networks -- remain one of deep learning's most perplexing phenomena despite nearly a decade of research. While numerous defenses and explanations have been…

Machine Learning · Computer Science 2025-09-16 Liv Gorton , Owen Lewis

The paper investigates the performance of state-of-the-art low-parameter deep neural networks for computer vision, focusing on bottleneck architectures and their behavior using superlinear activation functions. We address interference in…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Lilian Hollard , Lucas Mohimont , Nathalie Gaveau , Luiz-Angelo Steffenel

Many neural nets appear to represent data as linear combinations of "feature vectors." Algorithms for discovering these vectors have seen impressive recent success. However, we argue that this success is incomplete without an understanding…

Artificial Intelligence · Computer Science 2024-07-23 Martin Wattenberg , Fernanda B. Viégas

Many aesthetic models in computer vision suffer from two shortcomings: 1) the low descriptiveness and interpretability of those hand-crafted aesthetic criteria (i.e., nonindicative of region-level aesthetics), and 2) the difficulty of…

Computer Vision and Pattern Recognition · Computer Science 2019-08-09 Yanxiang Chen , Yuxing Hu , Luming Zhang , Ping Li , Chao Zhang

It is widely believed that complex machine learning models generally encode features through linear representations. This is the foundational hypothesis behind a vast body of work on interpretability. A key challenge toward extracting…

Machine Learning · Computer Science 2026-04-01 Allen Liu
‹ Prev 1 2 3 10 Next ›