From superposition to sparse codes: interpretable representations in neural networks

• URL: http://arxiv.org/abs/2503.01824v1
• Date: Mon, 03 Mar 2025 18:49:59 GMT
• Title: From superposition to sparse codes: interpretable representations in neural networks
• Authors: David Klindt, Charles O'Neill, Patrik Reizinger, Harald Maurer, Nina Miolane,
• Abstract summary: Recent evidence suggests that neural networks encode features in superposition, meaning that input concepts are linearly overlaid within the network's representations.<n>We present a perspective that explains this phenomenon and provides a foundation for extracting interpretable representations from neural activations.<n>Our arguments have implications for neural coding theories, AI transparency, and the broader goal of making deep learning models more interpretable.
• Score: 3.6738925004882685
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 features in superposition, meaning that input concepts are linearly overlaid within the network's representations. We present a perspective that explains this phenomenon and provides a foundation for extracting interpretable representations from neural activations. Our theoretical framework consists of three steps: (1) Identifiability theory shows that neural networks trained for classification recover latent features up to a linear transformation. (2) Sparse coding methods can extract disentangled features from these representations by leveraging principles from compressed sensing. (3) Quantitative interpretability metrics provide a means to assess the success of these methods, ensuring that extracted features align with human-interpretable concepts. By bridging insights from theoretical neuroscience, representation learning, and interpretability research, we propose an emerging perspective on understanding neural representations in both artificial and biological systems. Our arguments have implications for neural coding theories, AI transparency, and the broader goal of making deep learning models more interpretable.

Related papers

• Discovering Chunks in Neural Embeddings for Interpretability [53.80157905839065]
  We propose leveraging the principle of chunking to interpret artificial neural population activities.<n>We first demonstrate this concept in recurrent neural networks (RNNs) trained on artificial sequences with imposed regularities.<n>We identify similar recurring embedding states corresponding to concepts in the input, with perturbations to these states activating or inhibiting the associated concepts.
  arXiv  Detail & Related papers  (2025-02-03T20:30:46Z)
• 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)
• Graph Neural Networks for Learning Equivariant Representations of Neural Networks [55.04145324152541]
  We propose to represent neural networks as computational graphs of parameters. Our approach enables a single model to encode neural computational graphs with diverse architectures. We showcase the effectiveness of our method on a wide range of tasks, including classification and editing of implicit neural representations.
  arXiv  Detail & Related papers  (2024-03-18T18:01:01Z)
• Understanding polysemanticity in neural networks through coding theory [0.8702432681310401]
  We propose a novel practical approach to network interpretability and theoretical insights into polysemanticity and the density of codes. We show how random projections can reveal whether a network exhibits a smooth or non-differentiable code and hence how interpretable the code is. Our approach advances the pursuit of interpretability in neural networks, providing insights into their underlying structure and suggesting new avenues for circuit-level interpretability.
  arXiv  Detail & Related papers  (2024-01-31T16:31:54Z)
• Formal Conceptual Views in Neural Networks [0.0]
  We introduce two notions for conceptual views of a neural network, specifically a many-valued and a symbolic view. We test the conceptual expressivity of our novel views through different experiments on the ImageNet and Fruit-360 data sets. We demonstrate how conceptual views can be applied for abductive learning of human comprehensible rules from neurons.
  arXiv  Detail & Related papers  (2022-09-27T16:38:24Z)
• Searching for the Essence of Adversarial Perturbations [73.96215665913797]
  We show that adversarial perturbations contain human-recognizable information, which is the key conspirator responsible for a neural network's erroneous prediction. This concept of human-recognizable information allows us to explain key features related to adversarial perturbations.
  arXiv  Detail & Related papers  (2022-05-30T18:04:57Z)
• Interpretability of Neural Network With Physiological Mechanisms [5.1971653175509145]
  Deep learning continues to play as a powerful state-of-art technique that has achieved extraordinary accuracy levels in various domains of regression and classification tasks. The original goal of proposing the neural network model is to improve the understanding of complex human brains using a mathematical expression approach. Recent deep learning techniques continue to lose the interpretations of its functional process by being treated mostly as a black-box approximator.
  arXiv  Detail & Related papers  (2022-03-24T21:40:04Z)
• 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)
• Explainable artificial intelligence for mechanics: physics-informing neural networks for constitutive models [0.0]
  In mechanics, the new and active field of physics-informed neural networks attempts to mitigate this disadvantage by designing deep neural networks on the basis of mechanical knowledge. We propose a first step towards a physics-forming-in approach, which explains neural networks trained on mechanical data a posteriori. Therein, the principal component analysis decorrelates the distributed representations in cell states of RNNs and allows the comparison to known and fundamental functions.
  arXiv  Detail & Related papers  (2021-04-20T18:38:52Z)
• A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics [131.93113552146195]
  We present a new dataset, Handwritten arithmetic with INTegers (HINT), to examine machines' capability of learning generalizable concepts. In HINT, machines are tasked with learning how concepts are perceived from raw signals such as images. We undertake extensive experiments with various sequence-to-sequence models, including RNNs, Transformers, and GPT-3.
  arXiv  Detail & Related papers  (2021-03-02T01:32:54Z)
• Neuron-based explanations of neural networks sacrifice completeness and interpretability [67.53271920386851]
  We show that for AlexNet pretrained on ImageNet, neuron-based explanation methods sacrifice both completeness and interpretability. We show the most important principal components provide more complete and interpretable explanations than the most important neurons. Our findings suggest that explanation methods for networks like AlexNet should avoid using neurons as a basis for embeddings.
  arXiv  Detail & Related papers  (2020-11-05T21:26:03Z)

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.