Dynamical stability and chaos in artificial neural network trajectories along training
- URL: http://arxiv.org/abs/2404.05782v1
- Date: Mon, 8 Apr 2024 17:33:11 GMT
- Title: Dynamical stability and chaos in artificial neural network trajectories along training
- Authors: Kaloyan Danovski, Miguel C. Soriano, Lucas Lacasa,
- Abstract summary: We study the dynamical properties of this process by analyzing through this lens the network trajectories of a shallow neural network.
We find hints of regular and chaotic behavior depending on the learning rate regime.
This work also contributes to the cross-fertilization of ideas between dynamical systems theory, network theory and machine learning.
- Score: 3.379574469735166
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The process of training an artificial neural network involves iteratively adapting its parameters so as to minimize the error of the network's prediction, when confronted with a learning task. This iterative change can be naturally interpreted as a trajectory in network space -- a time series of networks -- and thus the training algorithm (e.g. gradient descent optimization of a suitable loss function) can be interpreted as a dynamical system in graph space. In order to illustrate this interpretation, here we study the dynamical properties of this process by analyzing through this lens the network trajectories of a shallow neural network, and its evolution through learning a simple classification task. We systematically consider different ranges of the learning rate and explore both the dynamical and orbital stability of the resulting network trajectories, finding hints of regular and chaotic behavior depending on the learning rate regime. Our findings are put in contrast to common wisdom on convergence properties of neural networks and dynamical systems theory. This work also contributes to the cross-fertilization of ideas between dynamical systems theory, network theory and machine learning
Related papers
- 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) - Exploiting Chaotic Dynamics as Deep Neural Networks [1.9282110216621833]
We show that the essence of chaos can be found in various state-of-the-art deep neural networks.
Our framework presents superior results in terms of accuracy, convergence speed, and efficiency.
This study offers a new path for the integration of chaos, which has long been overlooked in information processing.
arXiv Detail & Related papers (2024-05-29T22:03:23Z) - 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) - How neural networks learn to classify chaotic time series [77.34726150561087]
We study the inner workings of neural networks trained to classify regular-versus-chaotic time series.
We find that the relation between input periodicity and activation periodicity is key for the performance of LKCNN models.
arXiv Detail & Related papers (2023-06-04T08:53:27Z) - Identifying Equivalent Training Dynamics [3.793387630509845]
We develop a framework for identifying conjugate and non-conjugate training dynamics.
By leveraging advances in Koopman operator theory, we demonstrate that comparing Koopman eigenvalues can correctly identify a known equivalence between online mirror descent and online gradient descent.
We then utilize our approach to: (a) identify non-conjugate training dynamics between shallow and wide fully connected neural networks; (b) characterize the early phase of training dynamics in convolutional neural networks; (c) uncover non-conjugate training dynamics in Transformers that do and do not undergo grokking.
arXiv Detail & Related papers (2023-02-17T22:15:20Z) - 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) - Dynamic Analysis of Nonlinear Civil Engineering Structures using
Artificial Neural Network with Adaptive Training [2.1202971527014287]
In this study, artificial neural networks are developed with adaptive training algorithms.
The networks can successfully predict the time-history response of the shear frame and the rock structure to real ground motion records.
arXiv Detail & Related papers (2021-11-21T21:14:48Z) - 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) - Gradient Starvation: A Learning Proclivity in Neural Networks [97.02382916372594]
Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of features relevant for the task.
This work provides a theoretical explanation for the emergence of such feature imbalance in neural networks.
arXiv Detail & Related papers (2020-11-18T18:52:08Z) - A Principle of Least Action for the Training of Neural Networks [10.342408668490975]
We show the presence of a low kinetic energy displacement bias in the transport map of the network, and link this bias with generalization performance.
We propose a new learning algorithm, which automatically adapts to the complexity of the given task, and leads to networks with a high generalization ability even in low data regimes.
arXiv Detail & Related papers (2020-09-17T15:37:34Z) - Input-to-State Representation in linear reservoirs dynamics [15.491286626948881]
Reservoir computing is a popular approach to design recurrent neural networks.
The working principle of these networks is not fully understood.
A novel analysis of the dynamics of such networks is proposed.
arXiv Detail & Related papers (2020-03-24T00:14:25Z)
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.