Meta-Representational Predictive Coding: Neuroscience-Informed Self-Supervised Learning
cs.NE, cs.LG, q-bio.NC
Submitted: 2025-03-22
Updated: 2026-09-19
Comments: Significant re-org/clean-up/formatting and shifting of results to appendix/supplementary material (which now has a ToC)
Code: https://github.com/NACLab/encoder-only-predictive-coding
License: http://creativecommons.org/licenses/by/4.0/
The gist: Self-supervised learning has become an important paradigm in the domains of machine intelligence and computational neuroscience.
Terminology
Abstract
Self-supervised learning has become an important paradigm in the domains of machine intelligence and computational neuroscience. Nevertheless, current work on self-supervised learning (SSL) relies on biologically implausible credit assignment, i.e., backpropagation of errors, and feedforward inference, i.e., a sequential, non-parallel flow of information. Predictive coding (PC) offers a biologically plausible means to avoid backprop-specific limitations. However, unsupervised PC requires learning a generative model of raw input, which entails predicting high dimensional input; on the other hand, supervised PC learns a mapping between inputs to target labels and thus requires human annotation and incurs the drawbacks of supervised learning. In this work, we present a neuroscience-informed SSL model based on PC and active perception that we call meta-representational predictive coding (MPC). MPC sidesteps the need for a generative model of sensory input by learning to predict representations of data across parallel streams, resulting in an encoder-only learning-and-inference scheme.
Sources
- How Can We Be So Dense? The Benefits of Using Highly Sparse Representations
- Revisiting Feature Prediction for Learning Visual Representations from Video
- VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
- Exploration by Random Network Distillation
- Deep Predictive Coding Networks
- Video Representation Learning with Joint-Embedding Predictive Architectures
- Learning and Leveraging World Models in Visual Representation Learning
- Time-Integrated Spike-Timing-Dependent-Plasticity
- A Cookbook of Self-Supervised Learning
- Local Unsupervised Learning for Image Analysis
- HyperNetworks
- The Forward-Forward Algorithm: Some Preliminary Investigations
- Understanding Dimensional Collapse in Contrastive Self-supervised Learning
- Hebbian-Descent
- Hebbian learning with gradients: Hebbian convolutional neural networks with modern deep learning frameworks
- Representation Learning with Contrastive Predictive Coding
- Convolutional Neural Generative Coding: Scaling Predictive Coding to Natural Images
- The Predictive Forward-Forward Algorithm
- A Review of Neuroscience-Inspired Machine Learning
- Brain-Inspired Machine Intelligence: A Survey of Neurobiologically-Plausible Credit Assignment
Related papers
- Evolutionary Ensemble of Agents
- Encoding and Decoding Temporal Signals with Spiking Bandpass Wavelets
- Large Language Models and Evolutionary Computation: A Critical Review of Bidirectional Interaction, Automated Algorithm Design, and Co-Adaptive Systems
- Learning Alzheimer's Disease Signatures by bridging EEG with Spiking Neural Networks and Biophysical Simulations
- Investigating Hyperparameter Optimization and Transferability for ES-HyperNEAT: A TPE Approach
- S-AI-Recursive: A Bio-Inspired and Temporal Sparse AI Architecture for Iterative, Introspective, and Energy-Frugal Reasoning