Predictive Coding Can Do Exact Backpropagation on Convolutional and Recurrent Neural Networks

Predictive coding networks (PCNs) are an influential model for information processing in the brain. They have appealing theoretical interpretations and offer a single mechanism that accounts for diverse perceptual phenomena of the brain. On the other hand, backpropagation (BP) is commonly regarded to be the most successful learning method in modern machine learning. Thus, it is exciting that recent work formulates inference learning (IL) that trains PCNs to approximate BP. However, there are several remaining critical issues: (i) IL is an approximation to BP with unrealistic/non-trivial requirements, (ii) IL approximates BP in single-step weight updates; whether it leads to the same point as BP after the weight updates are conducted for more steps is unknown, and (iii) IL is computationally significantly more costly than BP. To solve these issues, a variant of IL that is strictly equivalent to BP in fully connected networks has been proposed. In this work, we build on this result by showing that it also holds for more complex architectures, namely, convolutional neural networks and (many-to-one) recurrent neural networks. To our knowledge, we are the first to show that a biologically plausible algorithm is able to exactly replicate the accuracy of BP on such complex architectures, bridging the existing gap between IL and BP, and setting an unprecedented performance for PCNs, which can now be considered as efficient alternatives to BP.

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

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

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

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

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

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

[7]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[8]  Karl J. Friston,et al.  A theory of cortical responses , 2005, Philosophical Transactions of the Royal Society B: Biological Sciences.

[9]  Pierre Baldi,et al.  A theory of local learning, the learning channel, and the optimality of backpropagation , 2015, Neural Networks.

[10]  Philip M. Long,et al.  The Singular Values of Convolutional Layers , 2018, ICLR.

[11]  Karl J. Friston,et al.  Cerebral hierarchies: predictive processing, precision and the pulvinar , 2015, Philosophical Transactions of the Royal Society B: Biological Sciences.

[12]  Alexander Ororbia,et al.  Biologically Motivated Algorithms for Propagating Local Target Representations , 2018, AAAI.

[13]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[14]  Xiaochao Dang,et al.  Supervised learning in spiking neural networks: A review of algorithms and evaluations , 2020, Neural Networks.

[15]  Karl J. Friston,et al.  Predictive coding explains binocular rivalry: An epistemological review , 2008, Cognition.

[16]  Karl J. Friston,et al.  Repetition suppression and its contextual determinants in predictive coding , 2016, Cortex.

[17]  Nikolaus Kriegeskorte,et al.  Deep Supervised, but Not Unsupervised, Models May Explain IT Cortical Representation , 2014, PLoS Comput. Biol..

[18]  Yoshua Bengio,et al.  Difference Target Propagation , 2014, ECML/PKDD.

[19]  A. Kitaoka,et al.  Illusory Motion Reproduced by Deep Neural Networks Trained for Prediction , 2018, Front. Psychol..

[20]  Daniel L. K. Yamins,et al.  A Task-Optimized Neural Network Replicates Human Auditory Behavior, Predicts Brain Responses, and Reveals a Cortical Processing Hierarchy , 2018, Neuron.

[21]  Karl J. Friston,et al.  Attention, Uncertainty, and Free-Energy , 2010, Front. Hum. Neurosci..

[22]  Wulfram Gerstner,et al.  Biologically plausible deep learning - but how far can we go with shallow networks? , 2019, Neural Networks.

[23]  Gabriel Kreiman,et al.  Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning , 2016, ICLR.

[24]  Karl J. Friston Learning and inference in the brain , 2003, Neural Networks.

[25]  Xiaohui Xie,et al.  Equivalence of Backpropagation and Contrastive Hebbian Learning in a Layered Network , 2003, Neural Computation.

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

[27]  Philipp Sterzer,et al.  A predictive coding account of bistable perception - a model-based fMRI study , 2017, PLoS Comput. Biol..