On the Dimension of Pullback Attractors in Recurrent Neural Networks
- URL: http://arxiv.org/abs/2501.11357v1
- Date: Mon, 20 Jan 2025 09:38:30 GMT
- Title: On the Dimension of Pullback Attractors in Recurrent Neural Networks
- Authors: Muhammed Fadera,
- Abstract summary: Recently, it has been conjectured that reservoir computers, a particular class of RNNs, trained on observations of a dynamical systems can be interpreted as embeddings.
In this work, we use a nonautonomous dynamical systems approach to establish an upper bound for the fractal dimension of the subset of reservoir state space approximated during training and prediction phase.
- Score: 0.0
- License:
- Abstract: Recurrent Neural Networks (RNNs) are high-dimensional state space models capable of learning functions on sequence data. Recently, it has been conjectured that reservoir computers, a particular class of RNNs, trained on observations of a dynamical systems can be interpreted as embeddings. This result has been established for the case of linear reservoir systems. In this work, we use a nonautonomous dynamical systems approach to establish an upper bound for the fractal dimension of the subset of reservoir state space approximated during training and prediction phase. We prove that when the input sequences comes from an Nin-dimensional invertible dynamical system, the fractal dimension of this set is bounded above by Nin. The result obtained here are useful in dimensionality reduction of computation in RNNs as well as estimating fractal dimensions of dynamical systems from limited observations of their time series. It is also a step towards understanding embedding properties of reservoir computers.
Related papers
- Deep Recurrent Stochastic Configuration Networks for Modelling Nonlinear Dynamic Systems [3.8719670789415925]
This paper proposes a novel deep reservoir computing framework, termed deep recurrent configuration network (DeepRSCN)
DeepRSCNs are incrementally constructed, with all reservoir nodes directly linked to the final output.
Given a set of training samples, DeepRSCNs can quickly generate learning representations, which consist of random basis functions with cascaded input readout weights.
arXiv Detail & Related papers (2024-10-28T10:33:15Z) - Metric-Entropy Limits on Nonlinear Dynamical System Learning [4.069144210024563]
We show that recurrent neural networks (RNNs) are capable of learning nonlinear systems that satisfy a Lipschitz property and forget past inputs fast enough in a metric-entropy optimal manner.
As the sets of sequence-to-sequence maps we consider are significantly more massive than function classes generally considered in deep neural network approximation theory, a refined metric-entropy characterization is needed.
arXiv Detail & Related papers (2024-07-01T12:57:03Z) - Gradient Descent in Neural Networks as Sequential Learning in RKBS [63.011641517977644]
We construct an exact power-series representation of the neural network in a finite neighborhood of the initial weights.
We prove that, regardless of width, the training sequence produced by gradient descent can be exactly replicated by regularized sequential learning.
arXiv Detail & Related papers (2023-02-01T03:18:07Z) - Deep learning delay coordinate dynamics for chaotic attractors from
partial observable data [0.0]
We utilize deep artificial neural networks to learn discrete discrete time maps and continuous time flows of the partial state.
We demonstrate the capacity of deep ANNs to predict chaotic behavior from a scalar observation on a manifold of dimension three via the Lorenz system.
arXiv Detail & Related papers (2022-11-20T19:25:02Z) - Learning Low Dimensional State Spaces with Overparameterized Recurrent
Neural Nets [57.06026574261203]
We provide theoretical evidence for learning low-dimensional state spaces, which can also model long-term memory.
Experiments corroborate our theory, demonstrating extrapolation via learning low-dimensional state spaces with both linear and non-linear RNNs.
arXiv Detail & Related papers (2022-10-25T14:45:15Z) - Analyzing Echo-state Networks Using Fractal Dimension [0.0]
We build on the observation that input sequences appear as fractal patterns in their hidden state representation.
These patterns have a fractal dimension that is lower than the number of units in the reservoir.
arXiv Detail & Related papers (2022-05-19T06:55:04Z) - Adaptive Machine Learning for Time-Varying Systems: Low Dimensional
Latent Space Tuning [91.3755431537592]
We present a recently developed method of adaptive machine learning for time-varying systems.
Our approach is to map very high (N>100k) dimensional inputs into the low dimensional (N2) latent space at the output of the encoder section of an encoder-decoder CNN.
This method allows us to learn correlations within and to track their evolution in real time based on feedback without interrupts.
arXiv Detail & Related papers (2021-07-13T16:05:28Z) - PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive
Learning [109.84770951839289]
We present PredRNN, a new recurrent network for learning visual dynamics from historical context.
We show that our approach obtains highly competitive results on three standard datasets.
arXiv Detail & Related papers (2021-03-17T08:28:30Z) - Online Limited Memory Neural-Linear Bandits with Likelihood Matching [53.18698496031658]
We study neural-linear bandits for solving problems where both exploration and representation learning play an important role.
We propose a likelihood matching algorithm that is resilient to catastrophic forgetting and is completely online.
arXiv Detail & Related papers (2021-02-07T14:19:07Z) - Liquid Time-constant Networks [117.57116214802504]
We introduce a new class of time-continuous recurrent neural network models.
Instead of declaring a learning system's dynamics by implicit nonlinearities, we construct networks of linear first-order dynamical systems.
These neural networks exhibit stable and bounded behavior, yield superior expressivity within the family of neural ordinary differential equations.
arXiv Detail & Related papers (2020-06-08T09:53:35Z)
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.