mlsanityData to 7 Oct 2026

Rational Neural Network Controllers

arXiv 2307.06287 ↗First posted 12 Jul 2023eess.SY cs.LG cs.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural networks have shown great success in many machine learning related tasks, due to their ability to act as general function approximators. Recent work has demonstrated the effectiveness of neural networks in control systems (known as neural feedback loops), most notably by using a neural network as a controller. However, one of the big challenges of this approach is that neural networks have been shown to be sensitive to adversarial attacks. This means that, unless they are designed properly, they are not an ideal candidate for controllers due to issues with robustness and uncertainty, which are pivotal aspects of control systems. There has been initial work on robustness to both analyse and design dynamical systems with neural network controllers. However, one prominent issue with these methods is that they use existing neural network architectures tailored for traditional machine learning tasks. These structures may not be appropriate for neural network controllers and it is important to consider alternative architectures. This paper considers rational neural networks and presents novel rational activation functions, which can be used effectively in robustness problems for neural feedback loops. Rational activation functions are replaced by a general rational neural network structure, which is convex in the neural network's parameters. A method is proposed to recover a stabilising controller from a Sum of Squares feasibility test. This approach is then applied to a refined rational neural network which is more compatible with Sum of Squares programming. Numerical examples show that this method can successfully recover stabilising rational neural network controllers for neural feedback loops with non-linear plants with noise and parametric uncertainty.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 52 references that are in the map. First posted on arXiv 12 Jul 2023.

Builds on

30 of 52 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  4. 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 610
  5. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 322
  6. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 209
  7. 2021Activation Functions in Deep Learning: A Comprehensive Survey and Benchmarkcited by 153
  8. 2017Deep Learning for Medical Image Processing: Overview, Challenges and Futurecited by 104
  9. 2018On the Power of Over-parametrization in Neural Networks with Quadratic Activationcited by 102
  10. 2019A Survey of Deep Learning Applications to Autonomous Vehicle Controlcited by 101
  11. 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
  12. 2020Rational neural networkscited by 75
18 more
  1. 2019Pad'e Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networkscited by 65
  2. 2020Stability Analysis using Quadratic Constraints for Systems with Neural Network Controllerscited by 42
  3. 2021Reachability Analysis of Neural Feedback Loopscited by 41
  4. 2017Neural networks and rational functionscited by 40
  5. 2020Enforcing robust control guarantees within neural network policiescited by 40
  6. 2020Imitation Learning with Stability and Safety Guaranteescited by 34
  7. 2018Universal Approximation with Quadratic Deep Networkscited by 29
  8. 2020Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learningcited by 23
  9. 2022QuadraLib: A Performant Quadratic Neural Network Library for Architecture Optimization and Design Explorationcited by 21
  10. 2021Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systemscited by 15
  11. 2021Neural Network Verification in Controlcited by 14
  12. 2019PowerNet: Efficient Representations of Polynomials and Smooth Functions by Deep Neural Networks with Rectified Power Unitscited by 12
  13. 2022Synthesis of Stabilizing Recurrent Equilibrium Network Controllerscited by 8
  14. 2021Linear systems with neural network nonlinearities: Improved stability analysis via acausal Zames-Falb multiplierscited by 6
  15. 2022Stability of Non-linear Neural Feedback Loops using Sum of Squarescited by 6
  16. 2021Chordal and factor-width decompositions for scalable semidefinite and polynomial optimizationcited by 4
  17. 2019Activation Adaptation in Neural Networkscited by 3
  18. 2017Improving Efficiency and Scalability of Sum of Squares Optimization: Recent Advances and Limitationscited by 1

Built on by

Not cited yet.