Gradient-free training of recurrent neural networks

• URL: http://arxiv.org/abs/2410.23467v1
• Date: Wed, 30 Oct 2024 21:24:34 GMT
• Title: Gradient-free training of recurrent neural networks
• Authors: Erik Lien Bolager, Ana Cukarska, Iryna Burak, Zahra Monfared, Felix Dietrich,
• Abstract summary: We introduce a computational approach to construct all weights and biases of a recurrent neural network without using gradient-based methods. The approach is based on a combination of random feature networks and Koopman operator theory for dynamical systems. In computational experiments on time series, forecasting for chaotic dynamical systems, and control problems, we observe that the training time and forecasting accuracy of the recurrent neural networks we construct are improved.
• Score: 3.272216546040443
• License:
• Abstract: Recurrent neural networks are a successful neural architecture for many time-dependent problems, including time series analysis, forecasting, and modeling of dynamical systems. Training such networks with backpropagation through time is a notoriously difficult problem because their loss gradients tend to explode or vanish. In this contribution, we introduce a computational approach to construct all weights and biases of a recurrent neural network without using gradient-based methods. The approach is based on a combination of random feature networks and Koopman operator theory for dynamical systems. The hidden parameters of a single recurrent block are sampled at random, while the outer weights are constructed using extended dynamic mode decomposition. This approach alleviates all problems with backpropagation commonly related to recurrent networks. The connection to Koopman operator theory also allows us to start using results in this area to analyze recurrent neural networks. In computational experiments on time series, forecasting for chaotic dynamical systems, and control problems, as well as on weather data, we observe that the training time and forecasting accuracy of the recurrent neural networks we construct are improved when compared to commonly used gradient-based methods.

Related papers

• Epistemic Modeling Uncertainty of Rapid Neural Network Ensembles for Adaptive Learning [0.0]
  A new type of neural network is presented using the rapid neural network paradigm. It is found that the proposed emulator embedded neural network trains near-instantaneously, typically without loss of prediction accuracy.
  arXiv  Detail & Related papers  (2023-09-12T22:34:34Z)
• 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)
• Continuous time recurrent neural networks: overview and application to forecasting blood glucose in the intensive care unit [56.801856519460465]
  Continuous time autoregressive recurrent neural networks (CTRNNs) are a deep learning model that account for irregular observations. We demonstrate the application of these models to probabilistic forecasting of blood glucose in a critical care setting.
  arXiv  Detail & Related papers  (2023-04-14T09:39:06Z)
• Neural Operator Learning for Long-Time Integration in Dynamical Systems with Recurrent Neural Networks [1.6874375111244329]
  Deep neural networks offer reduced computational costs during inference and can be trained directly from observational data. Existing methods, however, cannot extrapolate accurately and are prone to error accumulation in long-time integration. We address this issue by combining neural operators with recurrent neural networks, learning the operator mapping, while offering a recurrent structure to capture temporal dependencies.
  arXiv  Detail & Related papers  (2023-03-03T22:19:23Z)
• A predictive physics-aware hybrid reduced order model for reacting flows [65.73506571113623]
  A new hybrid predictive Reduced Order Model (ROM) is proposed to solve reacting flow problems. The number of degrees of freedom is reduced from thousands of temporal points to a few POD modes with their corresponding temporal coefficients. Two different deep learning architectures have been tested to predict the temporal coefficients.
  arXiv  Detail & Related papers  (2023-01-24T08:39:20Z)
• Global quantitative robustness of regression feed-forward neural networks [0.0]
  We adapt the notion of the regression breakdown point to regression neural networks. We compare the performance, measured by the out-of-sample loss, by a proxy of the breakdown rate. The results indeed motivate to use robust loss functions for neural network training.
  arXiv  Detail & Related papers  (2022-11-18T09:57:53Z)
• Spiking neural network for nonlinear regression [68.8204255655161]
  Spiking neural networks carry the potential for a massive reduction in memory and energy consumption. They introduce temporal and neuronal sparsity, which can be exploited by next-generation neuromorphic hardware. A framework for regression using spiking neural networks is proposed.
  arXiv  Detail & Related papers  (2022-10-06T13:04:45Z)
• An advanced spatio-temporal convolutional recurrent neural network for storm surge predictions [73.4962254843935]
  We study the capability of artificial neural network models to emulate storm surge based on the storm track/size/intensity history. This study presents a neural network model that can predict storm surge, informed by a database of synthetic storm simulations.
  arXiv  Detail & Related papers  (2022-04-18T23:42:18Z)
• Stochastic Recurrent Neural Network for Multistep Time Series Forecasting [0.0]
  We leverage advances in deep generative models and the concept of state space models to propose an adaptation of the recurrent neural network for time series forecasting. Our model preserves the architectural workings of a recurrent neural network for which all relevant information is encapsulated in its hidden states, and this flexibility allows our model to be easily integrated into any deep architecture for sequential modelling.
  arXiv  Detail & Related papers  (2021-04-26T01:43:43Z)
• Implicit recurrent networks: A novel approach to stationary input processing with recurrent neural networks in deep learning [0.0]
  In this work, we introduce and test a novel implementation of recurrent neural networks into deep learning. We provide an algorithm which implements the backpropagation algorithm on a implicit implementation of recurrent networks. A single-layer implicit recurrent network is able to solve the XOR problem, while a feed-forward network with monotonically increasing activation function fails at this task.
  arXiv  Detail & Related papers  (2020-10-20T18:55:32Z)
• 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.