Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control

• URL: http://arxiv.org/abs/2310.03915v3
• Date: Thu, 30 Nov 2023 15:50:46 GMT
• Title: Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control
• Authors: Neehal Tumma, Mathias Lechner, Noel Loo, Ramin Hasani, Daniela Rus
• Abstract summary: We show how a parameterization of recurrent connectivity influences robustness in closed-loop settings. We find that closed-form continuous-time neural networks (CfCs) with fewer parameters can outperform their full-rank, fully-connected counterparts.
• Score: 63.310780486820796
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Developing autonomous agents that can interact with changing environments is an open challenge in machine learning. Robustness is particularly important in these settings as agents are often fit offline on expert demonstrations but deployed online where they must generalize to the closed feedback loop within the environment. In this work, we explore the application of recurrent neural networks to tasks of this nature and understand how a parameterization of their recurrent connectivity influences robustness in closed-loop settings. Specifically, we represent the recurrent connectivity as a function of rank and sparsity and show both theoretically and empirically that modulating these two variables has desirable effects on network dynamics. The proposed low-rank, sparse connectivity induces an interpretable prior on the network that proves to be most amenable for a class of models known as closed-form continuous-time neural networks (CfCs). We find that CfCs with fewer parameters can outperform their full-rank, fully-connected counterparts in the online setting under distribution shift. This yields memory-efficient and robust agents while opening a new perspective on how we can modulate network dynamics through connectivity.

Related papers

• CaTs and DAGs: Integrating Directed Acyclic Graphs with Transformers and Fully-Connected Neural Networks for Causally Constrained Predictions [6.745494093127968]
  We introduce Causal Fully-Connected Neural Networks (CFCNs) and Causal Transformers (CaTs) CFCNs andCaTs operate under predefined causal constraints, as specified by a Directed Acyclic Graph (DAG) These models retain the powerful function approximation abilities of traditional neural networks while adhering to the underlying structural constraints.
  arXiv  Detail & Related papers  (2024-10-18T14:10:16Z)
• Adaptive control of recurrent neural networks using conceptors [1.9686770963118383]
  Recurrent Neural Networks excel at predicting and generating complex high-dimensional temporal patterns. In a Machine Learning setting, the network's parameters are adapted during a training phase to match the requirements of a given task/problem. We demonstrate how keeping parts of the network adaptive even after the training enhances its functionality and robustness.
  arXiv  Detail & Related papers  (2024-05-12T09:58:03Z)
• Deep Neural Networks Tend To Extrapolate Predictably [51.303814412294514]
  neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs. We observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD. We show how one can leverage our insights in practice to enable risk-sensitive decision-making in the presence of OOD inputs.
  arXiv  Detail & Related papers  (2023-10-02T03:25:32Z)
• A Generic Shared Attention Mechanism for Various Backbone Neural Networks [53.36677373145012]
  Self-attention modules (SAMs) produce strongly correlated attention maps across different layers. Dense-and-Implicit Attention (DIA) shares SAMs across layers and employs a long short-term memory module. Our simple yet effective DIA can consistently enhance various network backbones.
  arXiv  Detail & Related papers  (2022-10-27T13:24:08Z)
• Optimal Connectivity through Network Gradients for the Restricted Boltzmann Machine [0.0]
  A fundamental problem is efficiently finding connectivity patterns that improve the learning curve. Recent approaches explicitly include network connections as parameters that must be optimized in the model. This work presents a method to find optimal connectivity patterns for RBMs based on the idea of network gradients.
  arXiv  Detail & Related papers  (2022-09-14T21:09:58Z)
• Interference Cancellation GAN Framework for Dynamic Channels [74.22393885274728]
  We introduce an online training framework that can adapt to any changes in the channel. Our framework significantly outperforms recent neural network models on highly dynamic channels.
  arXiv  Detail & Related papers  (2022-08-17T02:01:18Z)
• Input correlations impede suppression of chaos and learning in balanced rate networks [58.720142291102135]
  Information encoding and learning in neural circuits depend on how well time-varying stimuli can control spontaneous network activity. We show that in firing-rate networks in the balanced state, external control of recurrent dynamics, strongly depends on correlations in the input.
  arXiv  Detail & Related papers  (2022-01-24T19:20:49Z)
• On the role of feedback in visual processing: a predictive coding perspective [0.6193838300896449]
  We consider deep convolutional networks (CNNs) as models of feed-forward visual processing and implement Predictive Coding (PC) dynamics. We find that the network increasingly relies on top-down predictions as the noise level increases. In addition, the accuracy of the network implementing PC dynamics significantly increases over time-steps, compared to its equivalent forward network.
  arXiv  Detail & Related papers  (2021-06-08T10:07:23Z)
• Faster Convergence in Deep-Predictive-Coding Networks to Learn Deeper Representations [12.716429755564821]
  Deep-predictive-coding networks (DPCNs) are hierarchical, generative models that rely on feed-forward and feed-back connections. A crucial element of DPCNs is a forward-backward inference procedure to uncover sparse states of a dynamic model. We propose an optimization strategy, with better empirical and theoretical convergence, based on accelerated proximal gradients.
  arXiv  Detail & Related papers  (2021-01-18T02:30:13Z)
• Network Diffusions via Neural Mean-Field Dynamics [52.091487866968286]
  We propose a novel learning framework for inference and estimation problems of diffusion on networks. Our framework is derived from the Mori-Zwanzig formalism to obtain an exact evolution of the node infection probabilities. Our approach is versatile and robust to variations of the underlying diffusion network models.
  arXiv  Detail & Related papers  (2020-06-16T18:45:20Z)

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.