# Active Sensing with Predictive Coding and Uncertainty Minimization

arXiv: https://arxiv.org/abs/2307.00668 · HTML: https://mlsanity.com/paper/2307.00668/

## 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 (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Planning to Explore via Self-Supervised World Models](https://mlsanity.com/paper/2005.05960/) (2020)
- [Recurrent Models of Visual Attention](https://mlsanity.com/paper/1406.6247/) (2014)
- [Provably Efficient Maximum Entropy Exploration](https://mlsanity.com/paper/1812.02690/) (2018)
- [Attend, Infer, Repeat: Fast Scene Understanding with Generative Models](https://mlsanity.com/paper/1603.08575/) (2016)
- [Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning](https://mlsanity.com/paper/1605.08104/) (2016)
- [DRAW: A Recurrent Neural Network For Image Generation](https://mlsanity.com/paper/1502.04623/) (2015)
- [Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models](https://mlsanity.com/paper/1507.00814/) (2015)
- [Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning](https://mlsanity.com/paper/1509.08731/) (2015)
- [Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects](https://mlsanity.com/paper/1806.01794/) (2018)
- [Dynamical Variational Autoencoders: A Comprehensive Review](https://mlsanity.com/paper/2008.12595/) (2020)
- [Model-Based Active Exploration](https://mlsanity.com/paper/1810.12162/) (2018)
- [Iterative Amortized Inference](https://mlsanity.com/paper/1807.09356/) (2018)
- [Fast active learning for pure exploration in reinforcement learning](https://mlsanity.com/paper/2007.13442/) (2020)
- [Toward Next-Generation Artificial Intelligence: Catalyzing the NeuroAI Revolution](https://mlsanity.com/paper/2210.08340/) (2022)
- [Predictive Coding: a Theoretical and Experimental Review](https://mlsanity.com/paper/2107.12979/) (2021)
- [BYOL-Explore: Exploration by Bootstrapped Prediction](https://mlsanity.com/paper/2206.08332/) (2022)
- [Continual Learning of Recurrent Neural Networks by Locally Aligning Distributed Representations](https://mlsanity.com/paper/1810.07411/) (2018)
- [Hybrid Predictive Coding: Inferring, Fast and Slow](https://mlsanity.com/paper/2204.02169/) (2022)
- [Backpropagation at the Infinitesimal Inference Limit of Energy-Based Models: Unifying Predictive Coding, Equilibrium Propagation, and Contrastive Hebbian Learning](https://mlsanity.com/paper/2206.02629/) (2022)
- [Deep Predictive Coding Network with Local Recurrent Processing for Object Recognition](https://mlsanity.com/paper/1805.07526/) (2018)
- [Predictive Coding, Variational Autoencoders, and Biological Connections](https://mlsanity.com/paper/2011.07464/) (2020)
- [VIME: Variational Information Maximizing Exploration](https://mlsanity.com/paper/1605.09674/) (2016)
- [Predictive Coding Can Do Exact Backpropagation on Convolutional and Recurrent Neural Networks](https://mlsanity.com/paper/2103.03725/) (2021)
- [Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards](https://mlsanity.com/paper/2012.13658/) (2020)
- [Backprop-Free Reinforcement Learning with Active Neural Generative Coding](https://mlsanity.com/paper/2107.07046/) (2021)
- [Active Predictive Coding: A Unified Neural Framework for Learning Hierarchical World Models for Perception and Planning](https://mlsanity.com/paper/2210.13461/) (2022)
- [Convolutional Neural Generative Coding: Scaling Predictive Coding to Natural Images](https://mlsanity.com/paper/2211.12047/) (2022)

## Built on by (most cited first, 5 of 5)

- [Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors](https://mlsanity.com/paper/2501.12633/) (2025)
- [Emergence of Fixational and Saccadic Movements in a Multi-Level Recurrent Attention Model for Vision](https://mlsanity.com/paper/2505.13191/) (2025)
- [Meta-Representational Predictive Coding: Neuroscience-Informed Self-Supervised Learning](https://mlsanity.com/paper/2503.21796/) (2025)
- [EVA: Bridging Performance and Human Alignment in Hard-Attention Vision Models for Image Classification](https://mlsanity.com/paper/2603.27340/) (2026)
- [Exploratory Experience Shapes the Geometry of Predictive Representations](https://mlsanity.com/paper/2605.27929/) (2026)

## 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.