Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
149 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

On the relationship between predictive coding and backpropagation (2106.13082v6)

Published 20 Jun 2021 in q-bio.NC, cs.LG, and cs.NE

Abstract: Artificial neural networks are often interpreted as abstract models of biological neuronal networks, but they are typically trained using the biologically unrealistic backpropagation algorithm and its variants. Predictive coding has been proposed as a potentially more biologically realistic alternative to backpropagation for training neural networks. This manuscript reviews and extends recent work on the mathematical relationship between predictive coding and backpropagation for training feedforward artificial neural networks on supervised learning tasks. Implications of these results for the interpretation of predictive coding and deep neural networks as models of biological learning are discussed along with a repository of functions, Torch2PC, for performing predictive coding with PyTorch neural network models.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (38)
  1. Izhikevich EM. Solving the distal reward problem through linkage of STDP and dopamine signaling. Cerebral cortex. 2007;17(10):2443–2452.
  2. Credit Assignment Through Broadcasting a Global Error Vector. arXiv preprint arXiv:210604089. 2021;.
  3. Backpropagation and the brain. Nature Reviews Neuroscience. 2020;21(6):335–346.
  4. Whittington JC, Bogacz R. Theories of error back-propagation in the brain. Trends in Cognitive Sciences. 2019;23(3):235–250.
  5. Urbanczik R, Senn W. Learning by the dendritic prediction of somatic spiking. Neuron. 2014;81(3):521–528.
  6. Random synaptic feedback weights support error backpropagation for deep learning. Nature Communications. 2016;7(1):1–10.
  7. Scellier B, Bengio Y. Equilibrium propagation: Bridging the gap between energy-based models and backpropagation. Frontiers in computational neuroscience. 2017;11:24.
  8. Cortical credit assignment by Hebbian, neuromodulatory and inhibitory plasticity. arXiv preprint arXiv:191100307. 2019;.
  9. Two routes to scalable credit assignment without weight symmetry. In: International Conference on Machine Learning. PMLR; 2020. p. 5511–5521.
  10. Burst-dependent synaptic plasticity can coordinate learning in hierarchical circuits. Nature Neuroscience. 2021; p. 1–10.
  11. Whittington JC, Bogacz R. An approximation of the error backpropagation algorithm in a predictive coding network with local hebbian synaptic plasticity. Neural Computation. 2017;29(5):1229–1262.
  12. Predictive coding approximates backprop along arbitrary computation graphs. arXiv preprint arXiv:200604182. 2020;.
  13. Can the brain do backpropagation?—exact implementation of backpropagation in predictive coding networks. Advances in Neural Information Processing Systems. 2020;33:22566.
  14. Predictive Coding Can Do Exact Backpropagation on Convolutional and Recurrent Neural Networks. arXiv preprint arXiv:210303725. 2021;.
  15. Rao RP, Ballard DH. Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects. Nature Neuroscience. 1999;2(1):79–87.
  16. Friston K. The free-energy principle: a unified brain theory? Nature Reviews Neuroscience. 2010;11(2):127–138.
  17. Huang Y, Rao RP. Predictive Coding. Wiley Interdisciplinary Reviews: Cognitive Science. 2011;2(5):580–593.
  18. Canonical microcircuits for predictive coding. Neuron. 2012;76(4):695–711.
  19. Clark A. Surfing uncertainty: Prediction, action, and the embodied mind. Oxford University Press; 2015.
  20. The free energy principle for action and perception: A mathematical review. Journal of Mathematical Psychology. 2017;81:55–79.
  21. Bogacz R. A tutorial on the free-energy framework for modelling perception and learning. Journal of Mathematical Psychology. 2017;76:198–211.
  22. Spratling MW. A review of predictive coding algorithms. Brain and cognition. 2017;112:92–97.
  23. Keller GB, Mrsic-Flogel TD. Predictive processing: a canonical cortical computation. Neuron. 2018;100(2):424–435.
  24. Deep Learning. MIT press Cambridge; 2016.
  25. Learning multiple layers of features from tiny images. Citeseer. 2009;.
  26. Predictive Coding: a Theoretical and Experimental Review. arXiv preprint arXiv:210712979. 2021;.
  27. Amari Si. Information geometry of the EM and em algorithms for neural networks. Neural networks. 1995;8(9):1379–1408.
  28. Brain-Score: Which Artificial Neural Network for Object Recognition is most Brain-Like? bioRxiv preprint. 2018;.
  29. Integrative Benchmarking to Advance Neurally Mechanistic Models of Human Intelligence. Neuron. 2020;.
  30. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:14091556. 2014;.
  31. Imagenet large scale visual recognition challenge. International Journal of Computer Vision. 2015;115(3):211–252.
  32. Hertäg L, Sprekeler H. Learning prediction error neurons in a canonical interneuron circuit. Elife. 2020;9:e57541.
  33. Learning from unexpected events in the neocortical microcircuit. bioRxiv. 2021;.
  34. Sensorimotor mismatch signals in primary visual cortex of the behaving mouse. Neuron. 2012;74(5):809–815.
  35. Zmarz P, Keller GB. Mismatch receptive fields in mouse visual cortex. Neuron. 2016;92(4):766–772.
  36. Visuomotor coupling shapes the functional development of mouse visual cortex. Cell. 2017;169(7):1291–1302.
  37. Predictive coding of novel versus familiar stimuli in the primary visual cortex. BioRxiv. 2017; p. 197608.
  38. PyTorch: An Imperative Style, High-Performance Deep Learning Library. Advances in Neural Information Processing Systems. 2019;32:8026–8037.
Citations (25)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now