Finite-time Lyapunov exponents of deep neural networks

• URL: http://arxiv.org/abs/2306.12548v1
• Date: Wed, 21 Jun 2023 20:21:23 GMT
• Title: Finite-time Lyapunov exponents of deep neural networks
• Authors: L. Storm, H. Linander, J. Bec, K. Gustavsson, B. Mehlig
• Abstract summary: We compute how small input perturbations affect the output of deep neural networks. We show that the maximal exponent forms geometrical structures in input space, akin to coherent structures in dynamical systems.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We compute how small input perturbations affect the output of deep neural networks, exploring an analogy between deep networks and dynamical systems, where the growth or decay of local perturbations is characterised by finite-time Lyapunov exponents. We show that the maximal exponent forms geometrical structures in input space, akin to coherent structures in dynamical systems. Ridges of large positive exponents divide input space into different regions that the network associates with different classes. These ridges visualise the geometry that deep networks construct in input space, shedding light on the fundamental mechanisms underlying their learning capabilities.

Related papers

• Revisiting Deep Information Propagation: Fractal Frontier and Finite-size Effects [16.42026346710591]
  We study information propagation in randomly neural networks with finite width and reveal that the boundary between ordered and chaotic regimes exhibits a fractal structure.<n>This shows the fundamental complexity of neural network dynamics, in a setting that is independent of input data and optimization.
  arXiv  Detail & Related papers  (2025-08-05T08:49:24Z)
• Task structure and nonlinearity jointly determine learned representational geometry [0.0]
  We show that Tanh networks tend to learn representations that reflect the structure of the target outputs, while ReLU networks retain more information about the structure of the raw inputs. Our findings shed light on the interplay between input-output geometry, nonlinearity, and learned representations in neural networks.
  arXiv  Detail & Related papers  (2024-01-24T16:14:38Z)
• The Evolution of the Interplay Between Input Distributions and Linear Regions in Networks [20.97553518108504]
  We count the number of linear convex regions in deep neural networks based on ReLU. In particular, we prove that for any one-dimensional input, there exists a minimum threshold for the number of neurons required to express it. We also unveil the iterative refinement process of decision boundaries in ReLU networks during training.
  arXiv  Detail & Related papers  (2023-10-28T15:04:53Z)
• Riemannian Residual Neural Networks [58.925132597945634]
  We show how to extend the residual neural network (ResNet) ResNets have become ubiquitous in machine learning due to their beneficial learning properties, excellent empirical results, and easy-to-incorporate nature when building varied neural networks.
  arXiv  Detail & Related papers  (2023-10-16T02:12:32Z)
• Deep neural networks architectures from the perspective of manifold learning [0.0]
  This paper is a comprehensive comparison and description of neural network architectures in terms of ge-ometry and topology. We focus on the internal representation of neural networks and on the dynamics of changes in the topology and geometry of a data manifold on different layers.
  arXiv  Detail & Related papers  (2023-06-06T04:57:39Z)
• Vanilla Feedforward Neural Networks as a Discretization of Dynamical Systems [9.382423715831687]
  In this paper, we back to the classical network structure and prove that the vanilla feedforward networks could also be a numerical discretization of dynamic systems. Our results could provide a new perspective for understanding the approximation properties of feedforward neural networks.
  arXiv  Detail & Related papers  (2022-09-22T10:32:08Z)
• Rank Diminishing in Deep Neural Networks [71.03777954670323]
  Rank of neural networks measures information flowing across layers. It is an instance of a key structural condition that applies across broad domains of machine learning. For neural networks, however, the intrinsic mechanism that yields low-rank structures remains vague and unclear.
  arXiv  Detail & Related papers  (2022-06-13T12:03:32Z)
• 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)
• A neural anisotropic view of underspecification in deep learning [60.119023683371736]
  We show that the way neural networks handle the underspecification of problems is highly dependent on the data representation. Our results highlight that understanding the architectural inductive bias in deep learning is fundamental to address the fairness, robustness, and generalization of these systems.
  arXiv  Detail & Related papers  (2021-04-29T14:31:09Z)
• Learning Contact Dynamics using Physically Structured Neural Networks [81.73947303886753]
  We use connections between deep neural networks and differential equations to design a family of deep network architectures for representing contact dynamics between objects. We show that these networks can learn discontinuous contact events in a data-efficient manner from noisy observations. Our results indicate that an idealised form of touch feedback is a key component of making this learning problem tractable.
  arXiv  Detail & Related papers  (2021-02-22T17:33:51Z)
• Depth-Width Trade-offs for Neural Networks via Topological Entropy [0.0]
  We show a new connection between the expressivity of deep neural networks and topological entropy from dynamical system. We discuss the relationship between topological entropy, the number of oscillations, periods and Lipschitz constant.
  arXiv  Detail & Related papers  (2020-10-15T08:14:44Z)
• Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
  We propose a topological perspective to represent a network into a complete graph for analysis. By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner. This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
  arXiv  Detail & Related papers  (2020-08-19T04:53:31Z)

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.