DMPCN: Dynamic Modulated Predictive Coding Network with Hybrid Feedback Representations

• URL: http://arxiv.org/abs/2504.14665v1
• Date: Sun, 20 Apr 2025 16:14:07 GMT
• Title: DMPCN: Dynamic Modulated Predictive Coding Network with Hybrid Feedback Representations
• Authors: A S M Sharifuzzaman Sagar, Yu Chen, Jun Hoong Chan,
• Abstract summary: This paper introduces a hybrid prediction error feedback mechanism with dynamic modulation for deep predictive coding networks.<n>We also present a loss function tailored to this framework to improve accuracy by focusing on precise prediction error minimization.<n> Experimental results demonstrate the superiority of our model over other approaches.
• Score: 2.9923113351846076
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Traditional predictive coding networks, inspired by theories of brain function, consistently achieve promising results across various domains, extending their influence into the field of computer vision. However, the performance of the predictive coding networks is limited by their error feedback mechanism, which traditionally employs either local or global recurrent updates, leading to suboptimal performance in processing both local and broader details simultaneously. In addition, traditional predictive coding networks face difficulties in dynamically adjusting to the complexity and context of varying input data, which is crucial for achieving high levels of performance in diverse scenarios. Furthermore, there is a gap in the development and application of specific loss functions that could more effectively guide the model towards optimal performance. To deal with these issues, this paper introduces a hybrid prediction error feedback mechanism with dynamic modulation for deep predictive coding networks by effectively combining global contexts and local details while adjusting feedback based on input complexity. Additionally, we present a loss function tailored to this framework to improve accuracy by focusing on precise prediction error minimization. Experimental results demonstrate the superiority of our model over other approaches, showcasing faster convergence and higher predictive accuracy in CIFAR-10, CIFAR-100, MNIST, and FashionMNIST datasets.

Related papers

• Precoder Learning for Weighted Sum Rate Maximization [5.305346885414619]
  We propose a novel deep neural network (DNN) to learn the precoder for weighted sum precoding (WSRM)<n>Compared to existing unitarys, the proposed DNN leverage the joint and permutation balances inherent in the optimal precoding policy.<n> Simulation results demonstrate that the proposed method significantly outperforms learning methods in terms of both learning and generalization performance.
  arXiv  Detail & Related papers  (2025-03-06T14:45:38Z)
• Imitation Learning of MPC with Neural Networks: Error Guarantees and Sparsification [5.260346080244568]
  We present a framework for bounding the approximation error in imitation model predictive controllers utilizing neural networks.<n>We discuss how this method can be used to design a stable neural network controller with performance guarantees.
  arXiv  Detail & Related papers  (2025-01-07T10:18:37Z)
• Neural Conformal Control for Time Series Forecasting [54.96087475179419]
  We introduce a neural network conformal prediction method for time series that enhances adaptivity in non-stationary environments.<n>Our approach acts as a neural controller designed to achieve desired target coverage, leveraging auxiliary multi-view data with neural network encoders.<n>We empirically demonstrate significant improvements in coverage and probabilistic accuracy, and find that our method is the only one that combines good calibration with consistency in prediction intervals.
  arXiv  Detail & Related papers  (2024-12-24T03:56:25Z)
• Diffusion Models as Network Optimizers: Explorations and Analysis [71.69869025878856]
  generative diffusion models (GDMs) have emerged as a promising new approach to network optimization.<n>In this study, we first explore the intrinsic characteristics of generative models.<n>We provide a concise theoretical and intuitive demonstration of the advantages of generative models over discriminative network optimization.
  arXiv  Detail & Related papers  (2024-11-01T09:05:47Z)
• 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)
• Generalization and Estimation Error Bounds for Model-based Neural Networks [78.88759757988761]
  We show that the generalization abilities of model-based networks for sparse recovery outperform those of regular ReLU networks. We derive practical design rules that allow to construct model-based networks with guaranteed high generalization.
  arXiv  Detail & Related papers  (2023-04-19T16:39:44Z)
• Predictive Coding Based Multiscale Network with Encoder-Decoder LSTM for Video Prediction [1.2537993038844142]
  We present a multi-scale predictive coding model for future video frames prediction. Our model employs a multi-scale approach (Coarse to Fine) where the higher level neurons generate coarser predictions (lower resolution) We propose several improvements to the training strategy to mitigate the accumulation of prediction errors in long-term prediction.
  arXiv  Detail & Related papers  (2022-12-22T12:15:37Z)
• Predictive coding, precision and natural gradients [2.1601966913620325]
  We show that hierarchical predictive coding networks with learnable precision are able to solve various supervised and unsupervised learning tasks. When applied to unsupervised auto-encoding of image inputs, the deterministic network produces hierarchically organized and disentangled embeddings.
  arXiv  Detail & Related papers  (2021-11-12T21:05:03Z)
• Semantic Perturbations with Normalizing Flows for Improved Generalization [62.998818375912506]
  We show that perturbations in the latent space can be used to define fully unsupervised data augmentations. We find that our latent adversarial perturbations adaptive to the classifier throughout its training are most effective.
  arXiv  Detail & Related papers  (2021-08-18T03:20:00Z)
• Predicting Deep Neural Network Generalization with Perturbation Response Curves [58.8755389068888]
  We propose a new framework for evaluating the generalization capabilities of trained networks. Specifically, we introduce two new measures for accurately predicting generalization gaps. We attain better predictive scores than the current state-of-the-art measures on a majority of tasks in the Predicting Generalization in Deep Learning (PGDL) NeurIPS 2020 competition.
  arXiv  Detail & Related papers  (2021-06-09T01:37:36Z)
• 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)

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.