Predictive Coding Graphs are a Superset of Feedforward Neural Networks
This work provides a theoretical foundation for exploring non-hierarchical neural network topologies in machine learning, though it is incremental as it builds on existing predictive coding models.
The paper proves that predictive coding graphs (PCGs) mathematically encompass feedforward neural networks, positioning PCGs as a superset within machine learning.
Predictive coding graphs (PCGs) are a recently introduced generalization to predictive coding networks, a neuroscience-inspired probabilistic latent variable model. Here, we prove how PCGs define a mathematical superset of feedforward artificial neural networks (multilayer perceptrons). This positions PCNs more strongly within contemporary machine learning (ML), and reinforces earlier proposals to study the use of non-hierarchical neural networks for ML tasks, and more generally the notion of topology in neural networks.