English
Related papers

Related papers: From superposition to sparse codes: interpretable …

200 papers

Single neurons in neural networks are often interpretable in that they represent individual, intuitively meaningful features. However, many neurons exhibit $\textit{mixed selectivity}$, i.e., they represent multiple unrelated features. A…

Machine Learning · Statistics 2023-10-19 David Klindt , Sophia Sanborn , Francisco Acosta , Frédéric Poitevin , Nina Miolane

Neural networks, specifically deep convolutional neural networks, have achieved unprecedented performance in various computer vision tasks, but the rationale for the computations and structures of successful neural networks is not fully…

Computer Vision and Pattern Recognition · Computer Science 2021-08-19 Joshua Bowren

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

Artificial Neural Networks form the basis of very powerful learning methods. It has been observed that a naive application of fully connected neural networks to data with many irrelevant variables often leads to overfitting. In an attempt…

Machine Learning · Computer Science 2020-02-12 Gitesh Dawer , Yangzi Guo , Sida Liu , Adrian Barbu

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

Interpretability benefits the theoretical understanding of representations. Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a…

Computation and Language · Computer Science 2023-06-27 Minxue Xia , Hao Zhu

Motivated by the hypothesis that neural network representations encode abstract, interpretable features as linearly accessible, approximately orthogonal directions, sparse autoencoders (SAEs) have become a popular tool in interpretability.…

Machine Learning · Computer Science 2025-11-05 Valérie Costa , Thomas Fel , Ekdeep Singh Lubana , Bahareh Tolooshams , Demba Ba

Brains learn to represent information from a large set of stimuli, typically by weak supervision. Unsupervised learning is therefore a natural approach for exploring the design of biological neural networks and their computations.…

Neurons and Cognition · Quantitative Biology 2025-10-17 Roy Urbach , Elad Schneidman

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

Despite strong empirical performance for image classification, deep neural networks are often regarded as ``black boxes'' and they are difficult to interpret. On the other hand, sparse convolutional models, which assume that a signal can be…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Xili Dai , Mingyang Li , Pengyuan Zhai , Shengbang Tong , Xingjian Gao , Shao-Lun Huang , Zhihui Zhu , Chong You , Yi Ma

Inspired by the robustness and efficiency of sparse representation in sparse coding based image restoration models, we investigate the sparsity of neurons in deep networks. Our method structurally enforces sparsity constraints upon hidden…

Computer Vision and Pattern Recognition · Computer Science 2020-06-09 Yuchen Fan , Jiahui Yu , Yiqun Mei , Yulun Zhang , Yun Fu , Ding Liu , Thomas S. Huang

Representation learning, and interpreting learned representations, are key areas of focus in machine learning and neuroscience. Both fields generally use representations as a means to understand or improve a system's computations. In this…

Machine Learning · Computer Science 2024-09-24 Andrew Kyle Lampinen , Stephanie C. Y. Chan , Katherine Hermann

Neural networks achieve remarkable performance through superposition: encoding multiple features as overlapping directions in activation space rather than dedicating individual neurons to each feature. This challenges interpretability, yet…

Machine Learning · Computer Science 2025-12-16 Leonard Bereska , Zoe Tzifa-Kratira , Reza Samavi , Efstratios Gavves

The prominent success of neural networks, mainly in computer vision tasks, is increasingly shadowed by their sensitivity to small, barely perceivable adversarial perturbations in image input. In this work, we aim at explaining this…

Computer Vision and Pattern Recognition · Computer Science 2023-11-15 Dana Weitzner , Raja Giryes

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

We introduce combinatorial interpretability, a methodology for understanding neural computation by analyzing the combinatorial structures in the sign-based categorization of a network's weights and biases. We demonstrate its power through…

Machine Learning · Computer Science 2025-05-07 Micah Adler , Dan Alistarh , Nir Shavit

Recent work in Deep Learning has re-imagined the representation of data as functions mapping from a coordinate space to an underlying continuous signal. When such functions are approximated by neural networks this introduces a compelling…

Machine Learning · Statistics 2022-08-09 Jonathan Richard Schwarz , Yee Whye Teh

Balancing predictive power and interpretability has long been a challenging research area, particularly in powerful yet complex models like neural networks, where nonlinearity obstructs direct interpretation. This paper introduces a novel…

Machine Learning · Computer Science 2025-02-20 Antoine Ledent , Peng Liu

Many approaches to transform classification problems from non-linear to linear by feature transformation have been recently presented in the literature. These notably include sparse coding methods and deep neural networks. However, many of…

Machine Learning · Computer Science 2015-07-08 Alessandro Montalto , Giovanni Tessitore , Roberto Prevete

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 ›