On Robust Classification using Contractive Hamiltonian Neural ODEs

• URL: http://arxiv.org/abs/2203.11805v1
• Date: Tue, 22 Mar 2022 15:16:36 GMT
• Title: On Robust Classification using Contractive Hamiltonian Neural ODEs
• Authors: Muhammad Zakwan, Liang Xu, Giancarlo Ferrari-Trecate
• Abstract summary: We employ contraction theory to improve robustness of neural ODEs (NODEs) In NODEs, the input data corresponds to the initial condition of dynamical systems. We propose a class of contractive Hamiltonian NODEs (CH-NODEs)
• Score: 8.049462923912902
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks can be fragile and sensitive to small input perturbations that might cause a significant change in the output. In this paper, we employ contraction theory to improve the robustness of neural ODEs (NODEs). A dynamical system is contractive if all solutions with different initial conditions converge to each other asymptotically. As a consequence, perturbations in initial conditions become less and less relevant over time. Since in NODEs, the input data corresponds to the initial condition of dynamical systems, we show contractivity can mitigate the effect of input perturbations. More precisely, inspired by NODEs with Hamiltonian dynamics, we propose a class of contractive Hamiltonian NODEs (CH-NODEs). By properly tuning a scalar parameter, CH-NODEs ensure contractivity by design and can be trained using standard backpropagation and gradient descent algorithms. Moreover, CH-NODEs enjoy built-in guarantees of non-exploding gradients, which ensures a well-posed training process. Finally, we demonstrate the robustness of CH-NODEs on the MNIST image classification problem with noisy test datasets.

Related papers

• Correctness Verification of Neural Networks Approximating Differential Equations [0.0]
  Neural Networks (NNs) approximate the solution of Partial Differential Equations (PDEs) NNs can become integral parts of simulation software tools which can accelerate the simulation of complex dynamic systems more than 100 times. This work addresses the verification of these functions by defining the NN derivative as a finite difference approximation. For the first time, we tackle the problem of bounding an NN function without a priori knowledge of the output domain.
  arXiv  Detail & Related papers  (2024-02-12T12:55:35Z)
• Ortho-ODE: Enhancing Robustness and of Neural ODEs against Adversarial Attacks [0.0]
  We show that by controlling the Lipschitz constant of the ODE dynamics the robustness can be significantly improved. We corroborate the enhanced robustness on numerous datasets.
  arXiv  Detail & Related papers  (2023-05-16T05:37:06Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• Reduced-PINN: An Integration-Based Physics-Informed Neural Networks for Stiff ODEs [0.0]
  Physics-informed neural networks (PINNs) have recently received much attention due to their capabilities in solving both forward and inverse problems. We propose a new PINN architecture, called Reduced-PINN, that utilizes a reduced-order integration method to enable the PINN to solve stiff chemical kinetics.
  arXiv  Detail & Related papers  (2022-08-23T09:20:42Z)
• Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State [66.2457134675891]
  Spiking neural networks (SNNs) are brain-inspired models that enable energy-efficient implementation on neuromorphic hardware. Most existing methods imitate the backpropagation framework and feedforward architectures for artificial neural networks. We propose a novel training method that does not rely on the exact reverse of the forward computation.
  arXiv  Detail & Related papers  (2021-09-29T07:46:54Z)
• Incorporating NODE with Pre-trained Neural Differential Operator for Learning Dynamics [73.77459272878025]
  We propose to enhance the supervised signal in learning dynamics by pre-training a neural differential operator (NDO) NDO is pre-trained on a class of symbolic functions, and it learns the mapping between the trajectory samples of these functions to their derivatives. We provide theoretical guarantee on that the output of NDO can well approximate the ground truth derivatives by proper tuning the complexity of the library.
  arXiv  Detail & Related papers  (2021-06-08T08:04:47Z)
• A unified framework for Hamiltonian deep neural networks [3.0934684265555052]
  Training deep neural networks (DNNs) can be difficult due to vanishing/exploding gradients during weight optimization. We propose a class of DNNs stemming from the time discretization of Hamiltonian systems. The proposed Hamiltonian framework, besides encompassing existing networks inspired by marginally stable ODEs, allows one to derive new and more expressive architectures.
  arXiv  Detail & Related papers  (2021-04-27T13:20:24Z)
• Neural ODE Processes [64.10282200111983]
  We introduce Neural ODE Processes (NDPs), a new class of processes determined by a distribution over Neural ODEs. We show that our model can successfully capture the dynamics of low-dimensional systems from just a few data-points.
  arXiv  Detail & Related papers  (2021-03-23T09:32:06Z)
• Meta-Solver for Neural Ordinary Differential Equations [77.8918415523446]
  We investigate how the variability in solvers' space can improve neural ODEs performance. We show that the right choice of solver parameterization can significantly affect neural ODEs models in terms of robustness to adversarial attacks.
  arXiv  Detail & Related papers  (2021-03-15T17:26:34Z)
• Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections [73.95786440318369]
  We focus on the so-called implicit effect' of GNIs, which is the effect of the injected noise on the dynamics of gradient descent (SGD) We show that this effect induces an asymmetric heavy-tailed noise on gradient updates. We then formally prove that GNIs induce an implicit bias', which varies depending on the heaviness of the tails and the level of asymmetry.
  arXiv  Detail & Related papers  (2021-02-13T21:28:09Z)
• Go with the Flow: Adaptive Control for Neural ODEs [10.265713480189484]
  We describe a new module called neurally controlled ODE (N-CODE) designed to improve the expressivity of NODEs. N-CODE modules are dynamic variables governed by a trainable map from initial or current activation state. A single module is sufficient for learning a distribution on non-autonomous flows that adaptively drive neural representations.
  arXiv  Detail & Related papers  (2020-06-16T22:21:15Z)

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.