Nonlinear Neural Dynamics and Classification Accuracy in Reservoir Computing

• URL: http://arxiv.org/abs/2411.10047v1
• Date: Fri, 15 Nov 2024 08:52:12 GMT
• Title: Nonlinear Neural Dynamics and Classification Accuracy in Reservoir Computing
• Authors: Claus Metzner, Achim Schilling, Andreas Maier, Patrick Krauss,
• Abstract summary: We study the accuracy of a reservoir computer in artificial classification tasks of varying complexity. We find that, even for activation functions with extremely reduced nonlinearity, weak recurrent interactions and small input signals, the reservoir is able to compute useful representations.
• Score: 3.196204482566275
• License:
• Abstract: Reservoir computing - information processing based on untrained recurrent neural networks with random connections - is expected to depend on the nonlinear properties of the neurons and the resulting oscillatory, chaotic, or fixpoint dynamics of the network. However, the required degree of nonlinearity and the range of suitable dynamical regimes for a given task are not fully understood. To clarify these questions, we study the accuracy of a reservoir computer in artificial classification tasks of varying complexity, while tuning the neuron's degree of nonlinearity and the reservoir's dynamical regime. We find that, even for activation functions with extremely reduced nonlinearity, weak recurrent interactions and small input signals, the reservoir is able to compute useful representations, detectable only in higher order principal components, that render complex classificiation tasks linearly separable for the readout layer. When increasing the recurrent coupling, the reservoir develops spontaneous dynamical behavior. Nevertheless, the input-related computations can 'ride on top' of oscillatory or fixpoint attractors without much loss of accuracy, whereas chaotic dynamics reduces task performance more drastically. By tuning the system through the full range of dynamical phases, we find that the accuracy peaks both at the oscillatory/chaotic and at the chaotic/fixpoint phase boundaries, thus supporting the 'edge of chaos' hypothesis. Our results, in particular the robust weakly nonlinear operating regime, may offer new perspectives both for technical and biological neural networks with random connectivity.

Related papers

• Unconditional stability of a recurrent neural circuit implementing divisive normalization [0.0]
  We prove the remarkable property of unconditional local stability for an arbitrary-dimensional ORGaNICs circuit. We show that ORGaNICs can be trained by backpropagation through time without gradient clipping/scaling.
  arXiv  Detail & Related papers  (2024-09-27T17:46:05Z)
• Heterogeneous quantization regularizes spiking neural network activity [0.0]
  We present a data-blind neuromorphic signal conditioning strategy whereby analog data are normalized and quantized into spike phase representations. We extend this mechanism by adding a data-aware calibration step whereby the range and density of the quantization weights adapt to accumulated input statistics.
  arXiv  Detail & Related papers  (2024-09-27T02:25:44Z)
• Absence of Closed-Form Descriptions for Gradient Flow in Two-Layer Narrow Networks [0.8158530638728501]
  We show that the dynamics of the gradient flow in two-layer narrow networks is not an integrable system. Under mild conditions, the identity component of the differential Galois group of the variational equations of the gradient flow is non-solvable. This result confirms the system's non-integrability and implies that the training dynamics cannot be represented by Liouvillian functions.
  arXiv  Detail & Related papers  (2024-08-15T17:40:11Z)
• 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)
• Addressing caveats of neural persistence with deep graph persistence [54.424983583720675]
  We find that the variance of network weights and spatial concentration of large weights are the main factors that impact neural persistence. We propose an extension of the filtration underlying neural persistence to the whole neural network instead of single layers. This yields our deep graph persistence measure, which implicitly incorporates persistent paths through the network and alleviates variance-related issues.
  arXiv  Detail & Related papers  (2023-07-20T13:34:11Z)
• 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)
• Amplifying Sine Unit: An Oscillatory Activation Function for Deep Neural Networks to Recover Nonlinear Oscillations Efficiently [0.0]
  In this work, we put forward a methodology based on deep neural networks with responsive layers structure to deal nonlinear oscillations in microelectromechanical systems. We have proposed a novel oscillatory activation function called Amplifying Sine Unit denoted as ASU which is more efficient than GCU for complex vibratory systems. Results show that the designed network with our proposed activation function ASU is more reliable and robust to handle the challenges posed by nonlinearity and oscillations.
  arXiv  Detail & Related papers  (2023-04-18T14:08:15Z)
• Globally Optimal Training of Neural Networks with Threshold Activation Functions [63.03759813952481]
  We study weight decay regularized training problems of deep neural networks with threshold activations. We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
  arXiv  Detail & Related papers  (2023-03-06T18:59:13Z)
• Exploring Linear Feature Disentanglement For Neural Networks [63.20827189693117]
  Non-linear activation functions, e.g., Sigmoid, ReLU, and Tanh, have achieved great success in neural networks (NNs) Due to the complex non-linear characteristic of samples, the objective of those activation functions is to project samples from their original feature space to a linear separable feature space. This phenomenon ignites our interest in exploring whether all features need to be transformed by all non-linear functions in current typical NNs.
  arXiv  Detail & Related papers  (2022-03-22T13:09:17Z)
• 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)
• Nonlinear computations in spiking neural networks through multiplicative synapses [3.1498833540989413]
  nonlinear computations can be implemented successfully in spiking neural networks. This requires supervised training and the resulting connectivity can be hard to interpret. We show how to directly derive the required connectivity for several nonlinear dynamical systems.
  arXiv  Detail & Related papers  (2020-09-08T16:47:27Z)

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.