Tightening the Biological Constraints on Gradient-Based Predictive Coding

Predictive coding (PC) is a general theory of cortical function. The local, gradient-based learning rules found in one kind of PC model have been shown to closely approximate back-propagation under certain conditions [18, 26, 32]. This finding suggests that this PC model may be useful for understanding how the brain solves the credit assignment problem. The model may also be useful for developing local learning algorithms that are compatible with neuromorphic hardware. In this paper, we modify this PC model so that it better fits biological constraints, including the constraints that neurons can only have positive firing rates and the constraint that synapses only flow in one direction. We also compute the gradient-based weight and activity updates given the modified activity values. We show that, under certain conditions, these modified PC networks perform as well or nearly as well on MNIST data as the unmodified PC model and networks trained with back-propagation.

[1]  M. Carandini,et al.  Normalization as a canonical neural computation , 2011, Nature Reviews Neuroscience.

[2]  David M. Blei,et al.  Variational Inference: A Review for Statisticians , 2016, ArXiv.

[3]  J. F. Kolen,et al.  Backpropagation without weight transport , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[4]  Michael W. Spratling,et al.  Unsupervised Learning of Overlapping Image Components Using Divisive Input Modulation , 2009, Comput. Intell. Neurosci..

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

[6]  Hong Wang,et al.  Loihi: A Neuromorphic Manycore Processor with On-Chip Learning , 2018, IEEE Micro.

[7]  Karl J. Friston,et al.  Predictive coding under the free-energy principle , 2009, Philosophical Transactions of the Royal Society B: Biological Sciences.

[8]  Chris Eliasmith,et al.  Neural Engineering: Computation, Representation, and Dynamics in Neurobiological Systems , 2004, IEEE Transactions on Neural Networks.

[9]  Johannes Schemmel,et al.  Demonstrating Hybrid Learning in a Flexible Neuromorphic Hardware System , 2016, IEEE Transactions on Biomedical Circuits and Systems.

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

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

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

[13]  Michael W. Spratling,et al.  Fitting predictive coding to the neurophysiological data , 2019, Brain Research.

[14]  Tomaso A. Poggio,et al.  Biologically-plausible learning algorithms can scale to large datasets , 2018, ICLR.

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

[16]  Alexander Ororbia,et al.  Spiking Neural Predictive Coding for Continual Learning from Data Streams , 2019, Neurocomputing.

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

[18]  Peter Dayan,et al.  Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems , 2001 .

[19]  J. Changeux,et al.  A Neuronal Model of Predictive Coding Accounting for the Mismatch Negativity , 2012, The Journal of Neuroscience.

[20]  Karl J. Friston,et al.  A free energy principle for the brain , 2006, Journal of Physiology-Paris.

[21]  Hesham Mostafa,et al.  Surrogate Gradient Learning in Spiking Neural Networks: Bringing the Power of Gradient-based optimization to spiking neural networks , 2019, IEEE Signal Processing Magazine.

[22]  Giacomo Indiveri,et al.  A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128K synapses , 2015, Front. Neurosci..

[23]  Gert Cauwenberghs,et al.  Deep Supervised Learning Using Local Errors , 2017, Front. Neurosci..

[24]  Beren Millidge,et al.  Relaxing the Constraints on Predictive Coding Models , 2020, ArXiv.

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

[26]  Michael W. Spratling.  Predictive coding as a model of biased competition in visual attention , 2008, Vision Research.

[27]  Floris P. de Lange,et al.  Predictive Coding in Sensory Cortex , 2015 .

[28]  Peter C. Humphreys,et al.  Deep Learning without Weight Transport , 2019, NeurIPS.

[29]  Daniel Kunin,et al.  Two Routes to Scalable Credit Assignment without Weight Symmetry , 2020, ICML.

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

[31]  David P. McGovern,et al.  Evaluating the neurophysiological evidence for predictive processing as a model of perception , 2020, Annals of the New York Academy of Sciences.

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