mlsanityData to 14 Oct 2026

Active Sensing with Predictive Coding and Uncertainty Minimization

arXiv 2307.00668 ↗First posted 2 Jul 2023cs.LG cs.NEcited by 5

Not on the map. Why?

Abstract (arXiv)

We present an end-to-end procedure for embodied exploration inspired by two biological computations: predictive coding and uncertainty minimization. The procedure can be applied to exploration settings in a task-independent and intrinsically driven manner. We first demonstrate our approach in a maze navigation task and show that it can discover the underlying transition distributions and spatial features of the environment. Second, we apply our model to a more complex active vision task, where an agent actively samples its visual environment to gather information. We show that our model builds unsupervised representations through exploration that allow it to efficiently categorize visual scenes. We further show that using these representations for downstream classification leads to superior data efficiency and learning speed compared to other baselines while maintaining lower parameter complexity. Finally, the modularity of our model allows us to probe its internal mechanisms and analyze the interaction between perception and action during exploration.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 33 of its 77 references that are in the map. First posted on arXiv 2 Jul 2023.

Builds on

33 of 77 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  4. 2020Planning to Explore via Self-Supervised World Modelscited by 368
  5. 2014Recurrent Models of Visual Attentioncited by 349
  6. 2018Provably Efficient Maximum Entropy Explorationcited by 242
  7. 2016Attend, Infer, Repeat: Fast Scene Understanding with Generative Modelscited by 209
  8. 2016Deep Predictive Coding Networks for Video Prediction and Unsupervised Learningcited by 204
  9. 2015DRAW: A Recurrent Neural Network For Image Generationcited by 191
  10. 2015Incentivizing Exploration In Reinforcement Learning With Deep Predictive Modelscited by 154
  11. 2015Variational Information Maximisation for Intrinsically Motivated Reinforcement Learningcited by 144
  12. 2018Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objectscited by 128
21 more
  1. 2020Dynamical Variational Autoencoders: A Comprehensive Reviewcited by 128
  2. 2018Model-Based Active Explorationcited by 105
  3. 2018Iterative Amortized Inferencecited by 94
  4. 2020Fast active learning for pure exploration in reinforcement learningcited by 92
  5. 2022Toward Next-Generation Artificial Intelligence: Catalyzing the NeuroAI Revolutioncited by 78
  6. 2021Predictive Coding: a Theoretical and Experimental Reviewcited by 77
  7. 2022BYOL-Explore: Exploration by Bootstrapped Predictioncited by 73
  8. 2018Continual Learning of Recurrent Neural Networks by Locally Aligning Distributed Representationscited by 32
  9. 2022Hybrid Predictive Coding: Inferring, Fast and Slowcited by 26
  10. 2022Backpropagation at the Infinitesimal Inference Limit of Energy-Based Models: Unifying Predictive Coding, Equilibrium Propagation, and Contrastive Hebbian Learningcited by 26
  11. 2018Deep Predictive Coding Network with Local Recurrent Processing for Object Recognitioncited by 25
  12. 2020Predictive Coding, Variational Autoencoders, and Biological Connectionscited by 21
  13. 2016VIME: Variational Information Maximizing Explorationcited by 16
  14. 2021Predictive Coding Can Do Exact Backpropagation on Convolutional and Recurrent Neural Networkscited by 14
  15. 2020Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewardscited by 13
  16. 2021Backprop-Free Reinforcement Learning with Active Neural Generative Codingcited by 12
  17. 2022Active Predictive Coding: A Unified Neural Framework for Learning Hierarchical World Models for Perception and Planningcited by 10
  18. 2022Convolutional Neural Generative Coding: Scaling Predictive Coding to Natural Imagescited by 10
  19. 2021Predictive Coding Theories of Cortical Functioncited by 6
  20. 2022Active Predictive Coding Networks: A Neural Solution to the Problem of Learning Reference Frames and Part-Whole Hierarchiescited by 6
  21. 2015Efficient Bayesian experimentation using an expected information gain lower boundcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviorscited by 6
  2. 2025Emergence of Fixational and Saccadic Movements in a Multi-Level Recurrent Attention Model for Visioncited by 3
  3. 2025Meta-Representational Predictive Coding: Neuroscience-Informed Self-Supervised Learningcited by 0
  4. 2026EVA: Bridging Performance and Human Alignment in Hard-Attention Vision Models for Image Classificationcited by 0
  5. 2026Exploratory Experience Shapes the Geometry of Predictive Representationscited by 0