On the relationship between predictive coding and backpropagation

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.

[1]  Beren Millidge,et al.  Predictive Coding Approximates Backprop Along Arbitrary Computation Graphs , 2020, Neural Computation.

[2]  Beren Millidge,et al.  Predictive Coding: a Theoretical and Experimental Review , 2021, ArXiv.

[3]  L. F. Abbott,et al.  Credit Assignment Through Broadcasting a Global Error Vector , 2021, NeurIPS.

[4]  Thomas Lukasiewicz,et al.  Predictive Coding Can Do Exact Backpropagation on Convolutional and Recurrent Neural Networks , 2021, ArXiv.

[5]  Yazan N. Billeh,et al.  Learning from unexpected events in the neocortical microcircuit , 2021, bioRxiv.

[6]  Jonas Kubilius,et al.  Integrative Benchmarking to Advance Neurally Mechanistic Models of Human Intelligence , 2020, Neuron.

[7]  Adam Santoro,et al.  Backpropagation and the brain , 2020, Nature Reviews Neuroscience.

[8]  Richard Naud,et al.  Burst-dependent synaptic plasticity can coordinate learning in hierarchical circuits , 2020, Nature Neuroscience.

[9]  L. Hertäg,et al.  Learning prediction error neurons in a canonical interneuron circuit , 2020, bioRxiv.

[10]  Daniel L. K. Yamins,et al.  Two Routes to Scalable Credit Assignment without Weight Symmetry , 2020, ICML.

[11]  Thomas Lukasiewicz,et al.  Can the Brain Do Backpropagation? - Exact Implementation of Backpropagation in Predictive Coding Networks , 2020, NeurIPS.

[12]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[13]  Claudia Clopath,et al.  Cortical credit assignment by Hebbian, neuromodulatory and inhibitory plasticity. , 2019, 1911.00307.

[14]  James C. R. Whittington,et al.  Theories of Error Back-Propagation in the Brain , 2019, Trends in Cognitive Sciences.

[15]  Georg B. Keller,et al.  Predictive Processing: A Canonical Cortical Computation , 2018, Neuron.

[16]  Jonas Kubilius,et al.  Brain-Score: Which Artificial Neural Network for Object Recognition is most Brain-Like? , 2018, bioRxiv.

[17]  Michael J. Berry,et al.  Predictive Coding of Novel versus Familiar Stimuli in the Primary Visual Cortex , 2017, bioRxiv.

[18]  Alexander Attinger,et al.  Visuomotor Coupling Shapes the Functional Development of Mouse Visual Cortex , 2017, Cell.

[19]  Simon McGregor,et al.  The free energy principle for action and perception: A mathematical review , 2017, 1705.09156.

[20]  M. Nour.  Surfing Uncertainty: Prediction, Action, and the Embodied Mind. , 2017, British Journal of Psychiatry.

[21]  Rafal Bogacz,et al.  An Approximation of the Error Backpropagation Algorithm in a Predictive Coding Network with Local Hebbian Synaptic Plasticity , 2017, Neural Computation.

[22]  Michael W. Spratling.  A review of predictive coding algorithms , 2017, Brain and Cognition.

[23]  Rafal Bogacz,et al.  A tutorial on the free-energy framework for modelling perception and learning , 2017, Journal of mathematical psychology.

[24]  Yoshua Bengio,et al.  Equilibrium Propagation: Bridging the Gap between Energy-Based Models and Backpropagation , 2016, Front. Comput. Neurosci..

[25]  Georg B. Keller,et al.  Mismatch Receptive Fields in Mouse Visual Cortex , 2016, Neuron.

[26]  Colin J. Akerman,et al.  Random synaptic feedback weights support error backpropagation for deep learning , 2016, Nature Communications.

[27]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[28]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[29]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[30]  W. Senn,et al.  Learning by the Dendritic Prediction of Somatic Spiking , 2014, Neuron.

[31]  Karl J. Friston,et al.  Canonical Microcircuits for Predictive Coding , 2012, Neuron.

[32]  Georg B. Keller,et al.  Sensorimotor Mismatch Signals in Primary Visual Cortex of the Behaving Mouse , 2012, Neuron.

[33]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[34]  W. Marsden.  I and J , 2012 .

[35]  Rajesh P. N. Rao,et al.  Predictive Coding , 2019, A Blueprint for the Hard Problem of Consciousness.

[36]  Karl J. Friston.  The free-energy principle: a unified brain theory? , 2010, Nature Reviews Neuroscience.

[37]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[38]  E. Izhikevich.  Solving the distal reward problem through linkage of STDP and dopamine signaling , 2007, BMC Neuroscience.

[39]  Rajesh P. N. Rao,et al.  Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects. , 1999 .

[40]  Shun-ichi Amari,et al.  Information geometry of the EM and em algorithms for neural networks , 1995, Neural Networks.