Deep Predictive Coding Network for Object Recognition

Abstract

Based on the predictive coding theory in neuroscience, we designed a bi-directional and recurrent neural net, namely deep predictive coding networks (PCN). It has feedforward, feedback, and recurrent connections. Feedback connections from a higher layer carry the prediction of its lower-layer representation; feedforward connections carry the prediction errors to its higher-layer. Given image input, PCN runs recursive cycles of bottom-up and top-down computation to update its internal representations and reduce the difference between bottom-up input and top-down prediction at every layer. After multiple cycles of recursive updating, the representation is used for image classification. With benchmark data (CIFAR-10/100, SVHN, and MNIST), PCN was found to always outperform its feedforward-only counterpart: a model without any mechanism for recurrent dynamics. Its performance tended to improve given more cycles of computation over time. In short, PCN reuses a single architecture to recursively run bottom-up and top-down processes. As a dynamical system, PCN can be unfolded to a feedforward model that becomes deeper and deeper over time, while refining it representation towards more accurate and definitive object recognition.

arXiv comment10 pages, 5 figures, 4 tables

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• FitNets: Hints for Thin Deep Nets
• Wide Residual Networks
• Training Very Deep Networks
• A guide to convolution arithmetic for deep learning
• Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathway
• Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
• Neural Encoding and Decoding with Deep Learning for Dynamic Natural Vision
• Deep Networks with Internal Selective Attention through Feedback Connections
• Deep Predictive Coding Networks
• CortexNet: a Generic Network Family for Robust Visual Temporal Representations

Cited by in corpus (19)

• Controversial stimuli: pitting neural networks against each other as models of human recognition
• Going in circles is the way forward: the role of recurrence in visual inference
• PreCNet: Next-Frame Video Prediction Based on Predictive Coding
• Predictive Coding: a Theoretical and Experimental Review
• Neural Networks with Recurrent Generative Feedback
• Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics
• A neural network trained to predict future video frames mimics critical properties of biological neuronal responses and perception
• PredNet and Predictive Coding: A Critical Review
• Bringing Giant Neural Networks Down to Earth with Unlabeled Data
• Disentangling neural mechanisms for perceptual grouping
• Stable and expressive recurrent vision models
• Visually-Guided Sound Source Separation with Audio-Visual Predictive Coding
• Robust neural circuit reconstruction from serial electron microscopy with convolutional recurrent networks
• Iterative VAE as a predictive brain model for out-of-distribution generalization
• Predictive coding feedback results in perceived illusory contours in a recurrent neural network
• CTNN: Corticothalamic-inspired neural network
• Perceptual Deep Neural Networks: Adversarial Robustness through Input Recreation
• Mathematical derivation of wave propagation properties in hierarchical neural networks with predictive coding feedback dynamics
• Hybrid Active Inference