English
Related papers

Related papers: On the Complexity of Neural Computation in Superpo…

200 papers

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

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

To understand cognitive reasoning in the brain, it has been proposed that symbols and compositions of symbols are represented by activity patterns (vectors) in a large population of neurons. Formal models implementing this idea [Plate…

Neural and Evolutionary Computing · Computer Science 2017-07-06 E. Paxon Frady , Denis Kleyko , Friedrich T. Sommer

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

As demonstrated in many areas of real-life applications, neural networks have the capability of dealing with high dimensional data. In the fields of optimal control and dynamical systems, the same capability was studied and verified in many…

Machine Learning · Computer Science 2020-12-04 Wei Kang , Qi Gong

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

We introduce a mathematical framework for the linear representation hypothesis (LRH), which asserts that intermediate layers of language models store features linearly. We separate the hypothesis into two claims: linear representation…

Machine Learning · Computer Science 2026-02-13 Nikhil Garg , Jon Kleinberg , Kenny Peng

Deep neural networks exhibit a simplicity bias, a well-documented tendency to favor simple functions over complex ones. In this work, we cast new light on this phenomenon through the lens of the Minimum Description Length principle,…

The main flaw of neural network ensembling is that it is exceptionally demanding computationally, especially, if the individual sub-models are large neural networks, which must be trained separately. Having in mind that modern DNNs can be…

Machine Learning · Computer Science 2020-03-31 Ludwik Bukowski , Witold Dzwinel

Artificial neural networks have gone through a recent rise in popularity, achieving state-of-the-art results in various fields, including image classification, speech recognition, and automated control. Both the performance and…

Neural and Evolutionary Computing · Computer Science 2016-11-08 Sean C. Smithson , Guang Yang , Warren J. Gross , Brett H. Meyer

Neural networks are capable of superposition -- representing more features than there are dimensions. Recent work considers the analogous concept for computation instead of storage, proposing theoretical constructions. But there has been…

Machine Learning · Computer Science 2025-07-15 Adam Newgas

A central idea in mechanistic interpretability is that neural networks represent more features than they have dimensions, arranging them in superposition to form an over-complete basis. This framing has been influential, motivating…

Machine Learning · Computer Science 2026-03-11 Lucas Prieto , Edward Stevinson , Melih Barsbey , Tolga Birdal , Pedro A. M. Mediano

We investigate the complexity of deep neural networks through the lens of functional equivalence, which posits that different parameterizations can yield the same network function. Leveraging the equivalence property, we present a novel…

Machine Learning · Computer Science 2024-05-17 Guohao Shen

We introduce a new notion of complexity of functions and we show that it has the following properties: (i) it governs a PAC Bayes-like generalization bound, (ii) for neural networks it relates to natural notions of complexity of functions…

Machine Learning · Computer Science 2023-03-15 Grzegorz Głuch , Rudiger Urbanke

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

Projecting fields between different meshes commonly arises in computational physics. This operation requires a supermesh construction and its computational cost is proportional to the number of cells of the supermesh $n$. Given any two…

Numerical Analysis · Mathematics 2023-01-10 M. Croci , P. E. Farrell

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

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

Superposition is an established decision procedure for a variety of first-order logic theories represented by sets of clauses. A satisfiable theory, saturated by superposition, implicitly defines a minimal term-generated model for the…

Artificial Intelligence · Computer Science 2009-11-30 Matthias Horbach , Christoph Weidenbach
‹ Prev 1 2 3 10 Next ›