Measuring the Representational Alignment of Neural Systems in Superposition

• URL: http://arxiv.org/abs/2604.00208v1
• Date: Tue, 31 Mar 2026 20:23:07 GMT
• Title: Measuring the Representational Alignment of Neural Systems in Superposition
• Abstract summary: We show that comparing neural systems in superposition requires extracting and aligning the underlying features rather than comparing the raw neural mixtures.<n>We argue that comparing neural systems in superposition requires extracting and aligning the underlying features rather than comparing the raw neural mixtures.
• Score: 4.843807818823007
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 similar activity patterns. However, neural systems frequently operate in superposition, encoding more features than they have neurons via linear compression. We derive closed-form expressions showing that superposition systematically deflates Representational Similarity Analysis, Centered Kernel Alignment, and linear regression, causing networks with identical feature content to appear dissimilar. The root cause is that these metrics are dependent on cross-similarity between two systems' respective superposition matrices, which under assumption of random projection usually differ significantly, not on the latent features themselves: alignment scores conflate what a system represents with how it represents it. Under partial feature overlap, this confound can invert the expected ordering, making systems sharing fewer features appear more aligned than systems sharing more. Crucially, the apparent misalignment need not reflect a loss of information; compressed sensing guarantees that the original features remain recoverable from the lower-dimensional activity, provided they are sparse. We therefore argue that comparing neural systems in superposition requires extracting and aligning the underlying features rather than comparing the raw neural mixtures.

Related papers

• Superposition disentanglement of neural representations reveals hidden alignment [6.015414975356222]
  In neuroscience and AI, representational alignment metrics measure the extent to which different deep neural networks (DNNs) or brains represent similar information.<n>We develop a theory for how the strict permutation metrics are dependent on superposition arrangements.<n>Our results suggest that superposition disentanglement is necessary for mapping metrics to uncover the true representational alignment between neural codes.
  arXiv  Detail & Related papers  (2025-10-03T17:12:40Z)
• Comparing noisy neural population dynamics using optimal transport distances [6.459101467083055]
  We show that existing metrics can fail to capture key differences between neural systems with noisy dynamic responses.<n>We then propose a metric for comparing the geometry of noisy neural trajectories.<n>We use the metric to compare models of neural responses in different regions of the motor system and to compare the dynamics of latent diffusion models for text-to-image synthesis.
  arXiv  Detail & Related papers  (2024-12-19T00:20:24Z)
• Decoupling Semantic Similarity from Spatial Alignment for Neural Networks [4.801683210246596]
  We argue that the spatial location of semantic objects does neither influence human perception nor deep learning classifiers. This should be reflected in the definition of similarity between image responses for computer vision systems. We measure semantic similarity between input responses by formulating it as a set-matching problem.
  arXiv  Detail & Related papers  (2024-10-30T15:17:58Z)
• Coding schemes in neural networks learning classification tasks [52.22978725954347]
  We investigate fully-connected, wide neural networks learning classification tasks. We show that the networks acquire strong, data-dependent features. Surprisingly, the nature of the internal representations depends crucially on the neuronal nonlinearity.
  arXiv  Detail & Related papers  (2024-06-24T14:50:05Z)
• Multilayer Multiset Neuronal Networks -- MMNNs [55.2480439325792]
  The present work describes multilayer multiset neuronal networks incorporating two or more layers of coincidence similarity neurons. The work also explores the utilization of counter-prototype points, which are assigned to the image regions to be avoided.
  arXiv  Detail & Related papers  (2023-08-28T12:55:13Z)
• Representational dissimilarity metric spaces for stochastic neural networks [4.229248343585332]
  Quantifying similarity between neural representations is a perennial problem in deep learning and neuroscience research. We generalize shape metrics to quantify differences in representations. We find that neurobiological oriented visual gratings and naturalistic scenes respectively resemble untrained and trained deep network representations.
  arXiv  Detail & Related papers  (2022-11-21T17:32:40Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Two-argument activation functions learn soft XOR operations like cortical neurons [6.88204255655161]
  We learn canonical activation functions with two input arguments, analogous to basal and apical dendrites. Remarkably, the resultant nonlinearities often produce soft XOR functions. Networks with these nonlinearities learn faster and perform better than conventional ReLU nonlinearities with matched parameter counts.
  arXiv  Detail & Related papers  (2021-10-13T17:06:20Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• The Separation Capacity of Random Neural Networks [78.25060223808936]
  We show that a sufficiently large two-layer ReLU-network with standard Gaussian weights and uniformly distributed biases can solve this problem with high probability. We quantify the relevant structure of the data in terms of a novel notion of mutual complexity.
  arXiv  Detail & Related papers  (2021-07-31T10:25:26Z)
• Redundant representations help generalization in wide neural networks [71.38860635025907]
  We study the last hidden layer representations of various state-of-the-art convolutional neural networks. We find that if the last hidden representation is wide enough, its neurons tend to split into groups that carry identical information, and differ from each other only by statistically independent noise.
  arXiv  Detail & Related papers  (2021-06-07T10:18:54Z)
• And/or trade-off in artificial neurons: impact on adversarial robustness [91.3755431537592]
  Presence of sufficient number of OR-like neurons in a network can lead to classification brittleness and increased vulnerability to adversarial attacks. We define AND-like neurons and propose measures to increase their proportion in the network. Experimental results on the MNIST dataset suggest that our approach holds promise as a direction for further exploration.
  arXiv  Detail & Related papers  (2021-02-15T08:19:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.