# Predictive Coding as a Neuromorphic Alternative to Backpropagation: A Critical Evaluation

arXiv: https://arxiv.org/abs/2304.02658 · HTML: https://mlsanity.com/paper/2304.02658/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 65 references that are in the map.
- First posted on arXiv 5 Apr 2023.

## Builds on (most cited first, 18 of 18)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Measuring the Effects of Data Parallelism on Neural Network Training](https://mlsanity.com/paper/1811.03600/) (2018)
- [Revisiting Small Batch Training for Deep Neural Networks](https://mlsanity.com/paper/1804.07612/) (2018)
- [Dendritic cortical microcircuits approximate the backpropagation algorithm](https://mlsanity.com/paper/1810.11393/) (2018)
- [Predictive Coding Approximates Backprop along Arbitrary Computation Graphs](https://mlsanity.com/paper/2006.04182/) (2020)
- [Deep Learning without Weight Transport](https://mlsanity.com/paper/1904.05391/) (2019)
- [The free energy principle for action and perception: A mathematical review](https://mlsanity.com/paper/1705.09156/) (2017)
- [Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?](https://mlsanity.com/paper/2202.09467/) (2022)
- [On the relationship between predictive coding and backpropagation](https://mlsanity.com/paper/2106.13082/) (2021)
- [A Theoretical Framework for Inference Learning](https://mlsanity.com/paper/2206.00164/) (2022)
- [Deep learning with asymmetric connections and Hebbian updates](https://mlsanity.com/paper/1812.07965/) (2018)
- [Predictive Coding Can Do Exact Backpropagation on Convolutional and Recurrent Neural Networks](https://mlsanity.com/paper/2103.03725/) (2021)
- [Meta-Learning Biologically Plausible Plasticity Rules with Random Feedback Pathways](https://mlsanity.com/paper/2210.16414/) (2022)
- [Relaxing the Constraints on Predictive Coding Models](https://mlsanity.com/paper/2010.01047/) (2020)
- [Activation Relaxation: A Local Dynamical Approximation to Backpropagation in the Brain](https://mlsanity.com/paper/2009.05359/) (2020)
- [Preventing Deterioration of Classification Accuracy in Predictive Coding Networks](https://mlsanity.com/paper/2208.07114/) (2022)
- [Curvature-Sensitive Predictive Coding with Approximate Laplace Monte Carlo](https://mlsanity.com/paper/2303.04976/) (2023)

## Built on by (most cited first, 8 of 8)

- [Brain-inspired Computational Intelligence via Predictive Coding](https://mlsanity.com/paper/2308.07870/) (2023)
- [Predictive Coding Networks and Inference Learning: Tutorial and Survey](https://mlsanity.com/paper/2407.04117/) (2024)
- [ePC: Fast and Deep Predictive Coding in Digital Simulation](https://mlsanity.com/paper/2505.20137/) (2025)
- [Training a Predictive Coding Network on ImageNet using Equilibrium Propagation](https://mlsanity.com/paper/2606.03584/) (2026)
- [Classification and Reconstruction Processes in Deep Predictive Coding Networks: Antagonists or Allies?](https://mlsanity.com/paper/2401.09237/) (2024)
- [Accelerated Predictive Coding Networks via Direct Kolen-Pollack Feedback Alignment](https://mlsanity.com/paper/2602.15571/) (2026)
- [Active Inference in Hebbian Learning Networks](https://mlsanity.com/paper/2306.05053/) (2023)
- [Bio-Inspired Artificial Neural Networks based on Predictive Coding](https://mlsanity.com/paper/2508.08762/) (2025)

## Abstract (arXiv)

Backpropagation has rapidly become the workhorse credit assignment algorithm for modern deep learning methods. Recently, modified forms of predictive coding (PC), an algorithm with origins in computational neuroscience, have been shown to result in approximately or exactly equal parameter updates to those under backpropagation. Due to this connection, it has been suggested that PC can act as an alternative to backpropagation with desirable properties that may facilitate implementation in neuromorphic systems. Here, we explore these claims using the different contemporary PC variants proposed in the literature. We obtain time complexity bounds for these PC variants which we show are lower-bounded by backpropagation. We also present key properties of these variants that have implications for neurobiological plausibility and their interpretations, particularly from the perspective of standard PC as a variational Bayes algorithm for latent probabilistic models. Our findings shed new light on the connection between the two learning frameworks and suggest that, in its current forms, PC may have more limited potential as a direct replacement of backpropagation than previously envisioned.