Unsupervised Learning of Generative and Discriminative Weights Encoding Elementary Image Components in a Predictive Coding Model of Cortical Function
The DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
Abstract
A method is presented for learning the reciprocal feedforward and feedback connections required by the predictive coding model of cortical function. When this method is used, feedforward and feedback connections are learned simultaneously and independently in a biologically plausible manner. The performance of the proposed algorithm is evaluated by applying it to learning the elementary components of artificial and natural images. For artificial images, the bars problem is employed, and the proposed algorithm is shown to produce state-of-the-art performance on this task. For natural images, components resembling Gabor functions are learned in the first processing stage, and neurons responsive to corners are learned in the second processing stage. The properties of these learned representations are in good agreement with neurophysiological data from V1 and V2. The proposed algorithm demonstrates for the first time that a single computational theory can explain the formation of cortical RFs and also the response properties of cortical neurons once those RFs have been learned.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Emergence of simple-cell receptive field properties by learning a sparse code for natural images
Olshausen, B. A., & Field, D. J. (1996) · Nature · doi:10.1038/381607a0 · Cited by 5,694 · cited 7×
“To demonstrate this, training data was generated using the same set of ten gray-scale images of natural scenes as was used in Olshausen and Field (1996a) 2 .”
BackgroundMethodInfluentialRao, R. P. N., & Ballard, D. H. (1999) · Nature Neuroscience · doi:10.1038/4580 · Cited by 5,483
Training Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879 · cited 1×
“In this respect the proposed algorithm is similar to the Helmholtz machine (Hinton et al., 1995; Weber and Triesch, 2008), the restricted Boltzmann machine (RBM; Hinton, 2002; Teh et al., 2003), and the encoder-decoder architecture (Ranzato et al., 2007).”
MethodA theory of cortical responses.
Friston, K. (2005) · Philosophical Transactions of the Royal Society B: Biological Sciences · doi:10.1098/rstb.2005.1622 · Cited by 4,578 · cited 1×
“…(Attneave, 1954; Barlow, 2001; Olshausen and Field, 1996b, 1997) and of hierarchical perceptual inference or analysis-by-synthesis (Barlow, 1994; Friston, 2005, 2009; Lee and Mumford, 2003; Mumford, 1992; Yuille and Kersten, 2006), hence, PC/BC can be related to these wider frameworks for…”
BackgroundSparse coding with an overcomplete basis set: A strategy employed by V1?
Olshausen, B. A., & Field, D. J. (1997) · Vision Research · doi:10.1016/s0042-6989(97)00169-7 · Cited by 3,642
Natural Image Statistics and Neural Representation
Simoncelli, E. P., & Olshausen, B. A. (2001) · Annual Review of Neuroscience · doi:10.1146/annurev.neuro.24.1.1193 · Cited by 2,460 · cited 1×
“One method to visualise the degree of independence between two neurons is to plot a conditional probability histogram (Schwartz and Simoncelli, 2001; Simoncelli and Olshausen, 2001; Wiltschut and Hamker, 2009).”
MethodConvolutional networks and applications in vision
LeCun, Y., Kavukcuoglu, K., & Farabet, C. (2010) · Proceedings of 2010 IEEE International Symposium on Circuits and Systems · doi:10.1109/iscas.2010.5537907 · Cited by 2,213 · cited 2×
“…belief networks (Hinton et al., 2006) and since the encoder-decoder architecture has been employed in recent versions of convolutional neural networks (Jarrett et al., 2009; LeCun et al., 2010), the full hierarchical PC/BC model can be related to these deep learning methods (Arel et al., 2010).”
MethodThe “independent components” of natural scenes are edge filters
Bell, A. J., & Sejnowski, T. J. (1997) · Vision Research · doi:10.1016/s0042-6989(97)00121-1 · Cited by 2,201
What is the best multi-stage architecture for object recognition?
Jarrett, K., Kavukcuoglu, K., Ranzato, M. A., & LeCun, Y. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459469 · Cited by 2,153
Normalization of cell responses in cat striate cortex
Heeger, D. J. (1992) · Visual Neuroscience · doi:10.1017/s0952523800009640 · Cited by 1,835
The free-energy principle: a rough guide to the brain?
Friston, K. (2009) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2009.04.005 · Cited by 1,831
Jones, J. P., & Palmer, L. A. (1987) · Journal of Neurophysiology · doi:10.1152/jn.1987.58.6.1233 · Cited by 1,658
Hierarchical Bayesian inference in the visual cortex
Lee, T. S., & Mumford, D. (2003) · Journal of the Optical Society of America A · doi:10.1364/josaa.20.001434 · Cited by 1,473 · cited 2×
“Predictive coding is itself a specific example of more general theories of efficient encoding or redundancy reduction (Attneave, 1954; Barlow, 2001; Olshausen and Field, 1996b, 1997) and of hierarchical perceptual inference or analysis-by-synthesis (Barlow, 1994; Friston, 2005, 2009; Lee and Mumford, 2003; Mumford, 19…”
BackgroundSparse coding of sensory inputs
Olshausen, B. A., & Field, D. J. (2004) · Current Opinion in Neurobiology · doi:10.1016/j.conb.2004.07.007 · Cited by 1,404
Object perception as Bayesian inference
Kersten, D., Mamassian, P., & Yuille, A. (2004) · Annual Review of Psychology · doi:10.1146/annurev.psych.55.090902.142005 · Cited by 1,269 · cited 2×
“• As a mechanism to perform ’explaining away’ in probabilistic inference (Kersten et al., 2004).”
BackgroundIndependent component filters of natural images compared with simple cells in primary visual cortex
van Hateren, J. H., & van der Schaaf, A. (1998) · Proceedings of the Royal Society of London. Series B: Biological Sciences · doi:10.1098/rspb.1998.0303 · Cited by 1,106
Efficient Learning of Sparse Representations with an Energy-Based Model
Ranzato, M., Poultney, C., Chopra, S., & LeCun, Y. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0147 · Cited by 1,106
On the computational architecture of the neocortex: II The role of cortico-cortical loops
Mumford, D. (1992) · Biological Cybernetics · doi:10.1007/bf00198477 · Cited by 1,074 · cited 1×
“…and Field, 1996b, 1997) and of hierarchical perceptual inference or analysis-by-synthesis (Barlow, 1994; Friston, 2005, 2009; Lee and Mumford, 2003; Mumford, 1992; Yuille and Kersten, 2006), hence, PC/BC can be related to these wider frameworks for understanding cortical function. e y e y e y (a)…”
BackgroundThe "Wake-Sleep" Algorithm for Unsupervised Neural Networks
Hinton, G. E., Dayan, P., Frey, B. J., & Neal, R. M. (1995) · Science · doi:10.1126/science.7761831 · Cited by 1,070
On the computational architecture of the neocortex: I. The role of the thalamo-cortical loop
Mumford, D. (1991) · Biological Cybernetics · doi:10.1007/bf00202389 · Cited by 929 · cited 2×
“Predictive coding itself is a specific example of more general theories of efficient encoding or redundancy reduction (Attneave, 1954; Barlow, 2001; Olshausen & Field, 1996b, 1997) and of hierarchical perceptual inference or analysis-by-synthesis (Barlow, 1994; Friston, 2005, 2009; Lee & Mumford, 2003; Mumford, 1992;…”
BackgroundVision as Bayesian inference: analysis by synthesis?
Yuille, A., & Kersten, D. (2006) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2006.05.002 · Cited by 849
Natural signal statistics and sensory gain control
Schwartz, O., & Simoncelli, E. P. (2001) · Nature Neuroscience · doi:10.1038/90526 · Cited by 835
Summation and Division by Neurons in Primate Visual Cortex
Carandini, M., & Heeger, D. J. (1994) · Science · doi:10.1126/science.8191289 · Cited by 649
Shunting Inhibition Modulates Neuronal Gain during Synaptic Excitation
Mitchell, S. J., & Silver, R. A. (2003) · Neuron · doi:10.1016/s0896-6273(03)00200-9 · Cited by 602
Motion selectivity and the contrast-response function of simple cells in the visual cortex
Albrecht, D. G., & Geisler, W. S. (1991) · Visual Neuroscience · doi:10.1017/s0952523800010336 · Cited by 433
Skottun, B. C., Bradley, A., Sclar, G., Ohzawa, I., & Freeman, R. D. (1987) · Journal of Neurophysiology · doi:10.1152/jn.1987.57.3.773 · Cited by 298
Representation of Concurrent Stimuli by Population Activity in Visual Cortex
Busse, L., Wade, A. R., & Carandini, M. (2009) · Neuron · doi:10.1016/j.neuron.2009.11.004 · Cited by 247 · cited 2×
“Previous models of V1 response properties (e.g., Adorján et al., 1999; Busse et al., 2009; Carandini et al., 2002; Cavanaugh et al., 2002; Dagoi and Sur, 2000; Priebe and Ferster, 2006; Sceniak et al., 1999; Schwabe et al., 2006; Somers et al., 1995; Stetter et al., 2000) can be categorised as descriptive models or st…”
MethodPredictive coding as a model of response properties in cortical area V1
Spratling, M. W. (2010) · The Journal of Neuroscience · doi:10.1523/jneurosci.4911-09.2010 · Cited by 206
Self-citationReconciling predictive coding and biased competition models of cortical function
Spratling, M. W. (2008) · Frontiers in Computational Neuroscience · doi:10.3389/neuro.10.004.2008 · Cited by 153
Self-citationPredictive feedback can account for biphasic responses in the lateral geniculate nucleus
Jehee, J. F. M., & Ballard, D. H. (2009) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1000373 · Cited by 75 · cited 3×
“It has recently been claimed that spatially segregated ON and OFF regions also emerge when a different implementation of Predictive Coding is applied to learning V1 RFs (Jehee and Ballard, 2009).”
BackgroundMethodInfluential
Cited by
Whatever next? Predictive brains, situated agents, and the future of cognitive science
Clark, A. (2013) · Behavioral and Brain Sciences · doi:10.1017/s0140525x12000477 · Cited by 5,924
A review of predictive coding algorithms
Spratling, M. W. (2017) · Brain and Cognition · doi:10.1016/j.bandc.2015.11.003 · Cited by 437
Self-citationDeep Predictive Coding Networks for Video Prediction and Unsupervised Learning
Lotter, W. E., Kreiman, G., & Cox, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.08104 · Cited by 368
A neural network trained for prediction mimics diverse features of biological neurons and perception
Lotter, W., Kreiman, G., & Cox, D. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-0170-9 · Cited by 128
Towards a Unified View on Pathways and Functions of Neural Recurrent Processing
Pennartz, C. M. A., Dora, S., Muckli, L., & Lorteije, J. A. M. (2019) · Trends in Neurosciences · doi:10.1016/j.tins.2019.07.005 · Cited by 73
“Whereas the original computational models focused on two-layer networks [44,45], PP can be used to train multilayer neural networks in an unsupervised manner using a neurobiologically plausible learning rule [48].”
Metadata
- Authors
- Spratling, M. W.
- Venue
- Neural Computation
- Publisher
- MIT Press - Journals
- Published
- 2012-01
- Volume
- 24
- Issue
- 1
- Pages
- 60-103
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W2158261978
- Cited by
- 67
- References
- 30
- FWCI
- 3.01
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.