A Hierarchical Predictive Coding Model of Object Recognition in Natural Images

Predictive coding has been proposed as a model of the hierarchical perceptual inference process performed in the cortex. However, results demonstrating that predictive coding is capable of performing the complex inference required to recognise objects in natural images have not previously been presented. This article proposes a hierarchical neural network based on predictive coding for performing visual object recognition. This network is applied to the tasks of categorising hand-written digits, identifying faces, and locating cars in images of street scenes. It is shown that image recognition can be performed with tolerance to position, illumination, size, partial occlusion, and within-category variation. The current results, therefore, provide the first practical demonstration that predictive coding (at least the particular implementation of predictive coding used here; the PC/BC-DIM algorithm) is capable of performing accurate visual object recognition.

• Publication year

  2016

• Venue

  Cognitive Computation

• Publication date

  2016-12-28

• Fields of study

  Medicine, Computer Science

• Identifiers
  DOI 10.1007/s12559-016-9445-1PMID 28413566PMCID 5371651
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• リアルタイム人口を用いたStacked denoising Autoencodersによるタクシー将来需要予測

  2017cited by this paper
• A review of predictive coding algorithms.

  2017cited by this paper
• A Semi-Supervised Predictive Sparse Decomposition Based on Task-Driven Dictionary Learning

  2017influential reference
• A neural implementation of Bayesian inference based on predictive coding

  2016cited by this paper
• Predictive coding as a model of cognition

  2016cited by this paper
• A neural implementation of the Hough transform and the advantages of explaining away

  2016influential reference
• I-theory on depth vs width: hierarchical function composition

  2015cited by this paper
• A Multiobjective Sparse Feature Learning Model for Deep Neural Networks

  2015cited by this paper
• Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines

  2015influential reference
• An Introduction to Model-Based Cognitive Neuroscience

  2015cited by this paper
• Predictive Coding in Sensory Cortex

  2015cited by this paper
• Deep Residual Learning for Image Recognition

  2015cited by this paper
• A neural model of binocular saccade planning and vergence control

  2015cited by this paper
• Unsupervised learning of digit recognition using spike-timing-dependent plasticity

  2015influential reference
• Encyclopedia of Computational Neuroscience

  2014cited by this paper
• Invariant Hough Random Ferns for Object Detection and Tracking

  2014cited by this paper
• Fast Image Recognition Based on Independent Component Analysis and Extreme Learning Machine

  2014influential reference
• Symbolic neural networks for cognitive capacities

  2014cited by this paper
• Are we predictive engines? Perils, prospects, and the puzzle of the porous perceiver.

  2013cited by this paper
• Deep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision?

  2013cited by this paper
• ImageNet Classification with Deep Convolutional Neural

  2013cited by this paper
• Real-time classification and sensor fusion with a spiking deep belief network

  2013influential reference
• Handwritten digit recognition using biologically inspired features

  2013influential reference
• Learning Component-Level Sparse Representation for Image and Video Categorization

  2013cited by this paper
• Classification using sparse representations: a biologically plausible approach

  2013influential reference
• Unsupervised learning of invariant representations with low sample complexity: the magic of sensory cortex or a new framework for machine learning?

  2013cited by this paper
• Whatever next? Predictive brains, situated agents, and the future of cognitive science.

  2013cited by this paper
• Simultaneous discriminative projection and dictionary learning for sparse representation based classification

  2013cited by this paper
• Extended Coding and Pooling in the HMAX Model

  2013cited by this paper
• Label Consistent K-SVD: Learning a Discriminative Dictionary for Recognition

  2013cited by this paper
• Representation Learning: A Review and New Perspectives

  2012cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• An Efficient Learning Procedure for Deep Boltzmann Machines

  2012cited by this paper
• How does the brain solve visual object recognition?

  2012cited by this paper
• Perceptual Inference Predicts Contextual Modulations of Sensory Responses

  2012cited by this paper
• Multi-column deep neural networks for image classification

  2012influential reference
• Unsupervised Learning of Generative and Discriminative Weights Encoding Elementary Image Components in a Predictive Coding Model of Cortical Function

  2012cited by this paper
• Neural processing as causal inference.

  2011cited by this paper
• Deep Sparse Rectifier Neural Networks

  2011influential reference
• Predictive coding.

  2011cited by this paper
• Learning a discriminative dictionary for sparse coding via label consistent K-SVD

  2011cited by this paper
• Hough Forests for Object Detection, Tracking, and Action Recognition

  2011cited by this paper
• Fast PRISM: Branch and Bound Hough Transform for Object Class Detection

  2011cited by this paper
• Online parts-based feature discovery using competitive activation neural networks

  2011cited by this paper
• Fisher Discrimination Dictionary Learning for sparse representation

  2011cited by this paper
• Sparse representation or collaborative representation: Which helps face recognition?

  2011cited by this paper
• Dictionary learning and sparse coding for unsupervised clustering

  2010influential reference
• Task-Driven Dictionary Learning

  2010influential reference
• Selectivity and Tolerance (“Invariance”) Both Increase as Visual Information Propagates from Cortical Area V4 to IT

  2010cited by this paper
• Discriminative K-SVD for dictionary learning in face recognition

  2010cited by this paper
• Deep, Big, Simple Neural Nets for Handwritten Digit Recognition

  2010influential reference
• The chains model for detecting parts by their context

  2010cited by this paper
• Invariance analysis of modified C2 features: case study—handwritten digit recognition

  2010cited by this paper
• Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion

  2010cited by this paper
• Convolutional networks and applications in vision

  2010cited by this paper
• What is the best multi-stage architecture for object recognition?

  2009influential reference
• Predictive coding under the free-energy principle

  2009cited by this paper
• Nonlinear Learning using Local Coordinate Coding

  2009influential reference
• Unsupervised Learning of Overlapping Image Components Using Divisive Input Modulation

  2009cited by this paper
• Exploring Strategies for Training Deep Neural Networks

  2009influential reference
• Robust Face Recognition via Sparse Representation

  2009influential reference
• Class-specific Hough forests for object detection

  2009cited by this paper
• Discriminative generalized hough transform for object dectection

  2009cited by this paper
• Predictive coding as a model of biased competition in visual attention.

  2008cited by this paper
• Supervised Dictionary Learning

  2008cited by this paper
• Modulating the Granularity of Category Formation by Global Cortical States

  2008cited by this paper
• Reconciling Predictive Coding and Biased Competition Models of Cortical Function

  2008cited by this paper
• Beyond sliding windows: Object localization by efficient subwindow search

  2008cited by this paper
• Why is Real-World Visual Object Recognition Hard?

  2008cited by this paper
• Robust Object Detection with Interleaved Categorization and Segmentation

  2008cited by this paper
• Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition

  2007influential reference
• Learning Deep Architectures for AI

  2007cited by this paper
• Robust Object Recognition with Cortex-Like Mechanisms

  2007cited by this paper
• Untangling invariant object recognition.

  2007cited by this paper
• Multiclass Object Recognition with Sparse, Localized Features

  2006cited by this paper
• A Fast Learning Algorithm for Deep Belief Nets

  2006influential reference
• Building the gist of a scene: the role of global image features in recognition.

  2006cited by this paper
• Supporting Online Material for Reducing the Dimensionality of Data with Neural Networks

  2006cited by this paper
• Acquiring linear subspaces for face recognition under variable lighting

  2005cited by this paper
• Restoring partly occluded patterns: a neural network model

  2005cited by this paper
• SpikeNet: real-time visual processing with one spike per neuron

  2004cited by this paper
• Object perception as Bayesian inference.

  2004cited by this paper
• Learning to detect objects in images via a sparse, part-based representation

  2004cited by this paper
• View from the Top: Hierarchies and Reverse Hierarchies in the Visual System

  2002cited by this paper
• Training Products of Experts by Minimizing Contrastive Divergence

  2002cited by this paper
• View from the top: hierarchies and reverse hierarchies in the visual system.

  2002cited by this paper
• Learning a Sparse Representation for Object Detection

  2002cited by this paper
• The Speed of Sight

  2001cited by this paper
• Is it a Bird? Is it a Plane? Ultra-Rapid Visual Categorisation of Natural and Artifactual Objects

  2001cited by this paper
• GradientBased Learning Applied to Document Recognition

  2001cited by this paper
• A Limit to the Speed of Processing in Ultra-Rapid Visual Categorization of Novel Natural Scenes

  2001cited by this paper
• From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose

  2001cited by this paper
• Learning to recognize objects

  2000cited by this paper
• Learning with Mixtures of Trees

  2000cited by this paper
• Hierarchical models of object recognition in cortex

  1999influential reference
• Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects.

  1999cited by this paper
• Learning to recognize objects.

  1999cited by this paper
• Seeing smells: imaging olfactory learning in bees

  1999cited by this paper
• Gradient-based learning applied to document recognition

  1998cited by this paper
• Convolutional networks for images, speech, and time series

  1998cited by this paper

• Probabilistic processing: Possible, probable, or preposterous? A dialectical essay

  2026cites this paper
• The 'design features' of language revisited.

  2025cites this paper
• A survey on neuro-mimetic deep learning via predictive coding

  2025cites this paper
• Circuit-level modeling of prediction error computation of multi-dimensional features in voluntary actions

  2025cites this paper
• A predictive approach to enhance time-series forecasting

  2024cites this paper
• Scientists Invent New Hypotheses, Do Brains?

  2024cites this paper
• Filter competition results in more robust Convolutional Neural Networks

  2024cites this paper
• Dissecting Mismatch Negativity: Early and Late Subcomponents for Detecting Deviants in Local and Global Sequence Regularities

  2023cites this paper
• Brain-Inspired Computational Intelligence via Predictive Coding

  2023cites this paper
• Saliency-Based Semantic Weeds Detection and Classification Using UAV Multispectral Imaging

  2023cites this paper
• Local minimization of prediction errors drives learning of invariant object representations in a generative network model of visual perception

  2023cites this paper
• Explaining away results in more robust visual tracking

  2022cites this paper
• Cross-domain learning for underwater image enhancement

  2022cites this paper
• It makes sense, so I see it better! Contextual information about the visual environment increases its perceived sharpness.

  2022cites this paper
• Convolutional Neural Generative Coding: Scaling Predictive Coding to Natural Images

  2022cites this paper
• Efficient Deep Reinforcement Learning with Predictive Processing Proximal Policy Optimization

  2022cites this paper
• SUBMITTED IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE

  2021cites this paper
• Performance of biologically grounded models of the early visual system on standard object recognition tasks

  2021cites this paper
• Learning image by-parts using early and late fusion of auto-encoder features

  2021cites this paper
• Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics

  2021cites this paper
• Learning Stable Deep Predictive Coding Networks with Weight Norm Supervision

  2021cites this paper
• Generative Models for Active Vision

  2021cites this paper
• Semantic and Physical Properties of Peripheral Vision Are Used for Scene Categorization in Central Vision

  2021cites this paper
• Biologically Plausible Training Mechanisms for Self-Supervised Learning in Deep Networks

  2021cites this paper
• Phase transitions in when feedback is useful

  2021cites this paper
• Banknote authenticity is signalled by rapid neural responses

  2021cites this paper
• Hierarchical Predictive Coding Models in a Deep-Learning Framework

  2020influential citation
• PreCNet: Next-Frame Video Prediction Based on Predictive Coding

  2020cites this paper
• Brain-inspired predictive coding dynamics improve the robustness of deep neural networks

  2020cites this paper
• Dense-CaptionNet: a Sentence Generation Architecture for Fine-grained Description of Image Semantics

  2020cites this paper
• Effect of Top-Down Connections in Hierarchical Sparse Coding

  2020cites this paper
• Motivated Cue-Integration and Emotion Regulation: Awareness of the Association Between Interoceptive and Exteroceptive Embodied Cues and Personal Need Creates an Emotion Goal

  2020cites this paper
• Predictive coding in auditory perception: challenges and unresolved questions

  2020cites this paper
• Do Process-1 simulations generate the epistemic feelings that drive Process-2 decision making?

  2020cites this paper
• Title: WHISKiT Physics: A three-dimensional mechanical model of the rat vibrissal array Running Title: Mechanics of the rat vibrissal array

  2019cites this paper
• Words are a context for mental inference.

  2019cites this paper
• Meaningful representations emerge from Sparse Deep Predictive Coding

  2019cites this paper
• Normalization and pooling in hierarchical models of natural images.

  2019cites this paper
• A Novel Semi-Supervised Convolutional Neural Network Method for Synthetic Aperture Radar Image Recognition

  2019cites this paper
• An intelligent system for paper currency verification using support vector machines

  2019cites this paper
• Discriminant Zero-Shot Learning with Center Loss

  2019cites this paper
• Cognitive Monitoring of Distributed Objects

  2019cites this paper
• Fitting Predictive Coding to the Neurophysiological Data.

  2019influential citation
• Are a Context for Mental Inference

  2019cites this paper
• Contemporary Natural Philosophy and Philosophies - Part 1

  2019cites this paper
• Explaining Away Results in Accurate and Tolerant Template Matching

  2019influential citation
• Sparse deep predictive coding captures contour integration capabilities of the early visual system

  2019cites this paper
• Interaction of top-down category-level expectation and bottom-up sensory input in early stages of visual-orthographic processing.

  2019cites this paper
• Predictive context biases binocular rivalry in children and adults with no positive relation to two measures of social cognition

  2019cites this paper
• Self-Organization of Spiking Neural Networks for Visual Object Recognition

  2019cites this paper
• WHISKiT Physics: A three-dimensional mechanical model of the rat vibrissal array

  2019cites this paper
• A Semi-Supervised CNN Method for SAR Image Recognition

  2019cites this paper
• Variational autoencoder: An unsupervised model for encoding and decoding fMRI activity in visual cortex

  2019cites this paper
• Sciences of Observation

  2018cites this paper
• Neural Image Caption Generation with Weighted Training and Reference

  2018cites this paper
• Visual and Category Representations Shaped by the Interaction Between Inferior Temporal and Prefrontal Cortices

  2018cites this paper
• Deep Belief Networks Based Feature Generation and Regression for Predicting Wind Power

  2018cites this paper
• A No-Reference Image Quality Measure for Blurred and Compressed Images Using Sparsity Features

  2018cites this paper
• Deep Predictive Coding Network for Object Recognition

  2018influential citation
• Reducing and Stretching Deep Convolutional Activation Features for Accurate Image Classification

  2018cites this paper
• Implicit Heterogeneous Features Embedding in Deep Knowledge Tracing

  2018cites this paper
• Clustering-Oriented Multiple Convolutional Neural Networks for Single Image Super-Resolution

  2018cites this paper
• A temporal neural network model for object recognition using a biologically plausible decision making layer

  2018cites this paper
• End-to-End ConvNet for Tactile Recognition Using Residual Orthogonal Tiling and Pyramid Convolution Ensemble

  2018cites this paper
• Deep Predictive Coding Network with Local Recurrent Processing for Object Recognition

  2018cites this paper
• A mosaic of Chu spaces and Channel Theory II: applications to object identification and mereological complexity

  2018cites this paper
• Semantic Category-Based Classification Using Nonlinear Features and Wavelet Coefficients of Brain Signals

  2017cites this paper
• Echo State Property of Deep Reservoir Computing Networks

  2017cites this paper
• Adaptive dynamic network architectures for companion systems

  2017cites this paper
• C ONTRASTIVE -S IGNAL -D EPENDENT P LASTICITY : F ORWARD -F ORWARD L EARNING OF S PIKING N EURAL S YSTEMS

  year unknowncites this paper