Learning Factorial Codes by Predictability Minimization
The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
I propose a novel general principle for unsupervised learning of distributed nonredundant internal representations of input patterns. The principle is based on two opposing forces. For each representational unit there is an adaptive predictor, which tries to predict the unit from the remaining units. In turn, each unit tries to react to the environment such that it minimizes its predictability. This encourages each unit to filter "abstract concepts" out of the environmental input such that these concepts are statistically independent of those on which the other units focus. I discuss various simple yet potentially powerful implementations of the principle that aim at finding binary factorial codes (Barlow et al. 1989), i.e., codes where the probability of the occurrence of a particular input is simply the product of the probabilities of the corresponding code symbols. Such codes are potentially relevant for (1) segmentation tasks, (2) speeding up supervised learning, and (3) novelty detection. Methods for finding factorial codes automatically implement Occam's razor for finding codes using a minimal number of units. Unlike previous methods the novel principle has a potential for removing not only linear but also nonlinear output redundancy. Illustrative experiments show that algorithms based on the principle of predictability minimization are practically feasible. The final part of this paper describes an entirely local algorithm that has a potential for learning unique representations of extended input sequences.
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
A Mathematical Theory of Communication
Shannon, C. E. (1948) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1948.tb00917.x · Cited by 48,949
Beyond regression : new fools for prediction and analysis in the behavioral sciences
Werbos, P. J. (1974) · Medical Entomology and Zoology · Cited by 2,739
Self-organization in a perceptual network
Linsker, R. (1988) · Computer · doi:10.1109/2.36 · Cited by 1,469
NEURAL NETWORKS, PRINCIPAL COMPONENTS, AND SUBSPACES
Oja, E. (1989) · International Journal of Neural Systems · doi:10.1142/s0129065789000475 · Cited by 821
Forming sparse representations by local anti-Hebbian learning
Földiák, P. (1990) · Biological Cybernetics · doi:10.1007/bf02331346 · Cited by 528
Learning Complex, Extended Sequences Using the Principle of History Compression
Schmidhuber, J. (1992) · Neural Computation · doi:10.1162/neco.1992.4.2.234 · Cited by 398
Self-citationBarlow, H. B., Kaushal, T. P., & Mitchison, G. J. (1989) · Neural Computation · doi:10.1162/neco.1989.1.3.412 · Cited by 202
Development of feature detectors by self-organization: A network model
Rubner, J., & Schulten, K. (1990) · Biological Cybernetics · doi:10.1007/bf00198094 · Cited by 169
UNSUPERVISED LEARNING PROCEDURES FOR NEURAL NETWORKS
Becker, S. (1991) · International Journal of Neural Systems · doi:10.1142/s0129065791000030 · Cited by 114
An Optimality Principle for Unsupervised Learning
Sanger, T. D. (1988) · Cited by 104
Cited by
GAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Self-citationA Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714
“There are various definitions for disentanglement [50, 46, 1, 6, 18], but a common goal is a latent space that consists of linear subspaces, each of which controls one factor of variation.”
BackgroundAn Information-Maximization Approach to Blind Separation and Blind Deconvolution
Bell, A. J., & Sejnowski, T. J. (1995) · Neural Computation · doi:10.1162/neco.1995.7.6.1129 · Cited by 8,986
Deep Unsupervised Learning using Nonequilibrium Thermodynamics
Sohl-Dickstein, J., Weiss, E. A., Maheswaranathan, N., & Ganguli, S. (2015) · arXiv · doi:10.48550/arxiv.1503.03585 · Cited by 2,637
“A similar objective in (Schmidhuber, 1992) learns a two-way mapping to a representation with marginally independent units.”
BackgroundLearning deep representations by mutual information estimation and maximization
Hjelm, R. D., Fedorov, A., Lavoie-Marchildon, S., Grewal, K., Bachman, P., Trischler, A., & Bengio, Y. (2018) · arXiv · doi:10.48550/arxiv.1808.06670 · Cited by 1,991
Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction
Masci, J., Meier, U., Cireşan, D., & Schmidhuber, J. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-21735-7_7 · Cited by 1,955
Self-citationA Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
Gui, J., Sun, Z., Wen, Y., Tao, D., & Ye, J. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3130191 · Cited by 1,231
“relevant work is predictability minimization [2].”
What Is the Goal of Sensory Coding?
Field, D. J. (1994) · Neural Computation · doi:10.1162/neco.1994.6.4.559 · Cited by 1,183
Interpretable machine learning: Fundamental principles and 10 grand challenges
Rudin, C., Chen, C., Chen, Z., Huang, H., Semenova, L., & Zhong, C. (2022) · Statistics Surveys · doi:10.1214/21-ss133 · Cited by 958
A Unifying Review of Deep and Shallow Anomaly Detection
Ruff, L., Kauffmann, J. R., Vandermeulen, R. A., Montavon, G., Samek, W., Kloft, M., Dietterich, T. G., & Muller, K.-R. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3052449 · Cited by 914
Generative adversarial networks: introduction and outlook
Wang, K., Gou, C., Duan, Y., Lin, Y., Zheng, X., & Wang, F.-Y. (2017) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2017.7510583 · Cited by 806
Local feature analysis: a general statistical theory for object representation
Penev, P. S., & Atick, J. J. (1996) · Network Computation in Neural Systems · doi:10.1088/0954-898x/7/3/002 · Cited by 627
Kim, H., & Mnih, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.05983 · Cited by 617
Learning Complex, Extended Sequences Using the Principle of History Compression
Schmidhuber, J. (1992) · Neural Computation · doi:10.1162/neco.1992.4.2.234 · Cited by 398
Self-citationSparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
Marks, S., Rager, C., Michaud, E. J., Belinkov, Y., Bau, D., & Mueller, A. (2024) · arXiv · doi:10.48550/arxiv.2403.19647 · Cited by 295
Towards Visually Explaining Variational Autoencoders
Liu, W., Li, R., Zheng, M., Karanam, S., Wu, Z., Bhanu, B., Radke, R. J., & Camps, O. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00867 · Cited by 294
Visual Reinforcement Learning with Imagined Goals
Nair, A., Pong, V. H., Dalal, M., Bahl, S., Lin, S., & Levine, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.04742 · Cited by 288
Fader Networks: Manipulating Images by Sliding Attributes
Lample, G., Zeghidour, N., Usunier, N., Bordes, A., Denoyer, L., & Ranzato, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.00409 · Cited by 271
A survey on generative adversarial networks for imbalance problems in computer vision tasks
Sampath, V., Maurtua, I., Aguilar Martín, J. J., & Gutierrez, A. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00414-0 · Cited by 259
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
Gui, J., Sun, Z., Wen, Y., Tao, D., & Ye, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.06937 · Cited by 253
Adversarial Latent Autoencoders
Pidhorskyi, S., Adjeroh, D. A., & Doretto, G. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01411 · Cited by 233
Darla Improving zero-shot transfer in reinforcement learning
Higgins, I., Pal, A., Rusu, A. A., Matthey, L., Burgess, C. P., Pritzel, A., Botvinick, M., Blundell, C., & Lerchner, A. (2017) · arXiv · doi:10.48550/arxiv.1707.08475 · Cited by 219
Catastrophic forgetting and mode collapse in GANs
Thanh-Tung, H., & Tran, T. (2020) · 2020 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207181 · Cited by 214
“INTRODUCTION GANs [1, 2] are a powerful tool for modeling complex distributions.”
MethodLearning Adversarially Fair and Transferable Representations
Madras, D., Creager, E., Pitassi, T., & Zemel, R. S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.06309 · Cited by 171
“, 2016), although similar concepts had previously been proposed for unsupervised and supervised learning (Schmidhuber, 1992; Gutmann & Hyvärinen, 2010).”
BackgroundContext-Aware Generative Adversarial Privacy
Huang, C., Kairouz, P., Chen, X., Sankar, L., & Rajagopal, R. (2017) · Entropy · doi:10.3390/e19120656 · Cited by 156
On the Binding Problem in Artificial Neural Networks
Greff, K., van Steenkiste, S., & Schmidhuber, J. (2020) · arXiv · doi:10.48550/arxiv.2012.05208 · Cited by 102
“Alternatively, Bengio (2019) argues for the importance of a low-dimensional ‘conscious state’ (working memory) composed of largely independent units of abstraction that can be selected via attention (perhaps reminiscient of Schmidhuber, 1992b).”
BackgroundInfluentialSelf-citationSchmidhuber, J. (2003) · Natural Computing Series · doi:10.1007/978-3-642-18965-4_23 · Cited by 65
Self-citationMeasuring Disentanglement: A Review of Metrics
Carbonneau, M.-A., Zaidi, J., Boilard, J., & Gagnon, G. (2020) · arXiv · doi:10.48550/arxiv.2012.09276 · Cited by 52
“While there is no unanimously accepted definition of disentanglement, most agree on two main aspects [9], [14], [18], [26], [30], [31].”
BackgroundCompressive Privacy Generative Adversarial Network
Tseng, B.-W., & Wu, P.-Y. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.2968188 · Cited by 48
Metadata
- Authors
- Schmidhuber, J.
- Venue
- Neural Computation
- Publisher
- MIT Press - Journals
- Published
- 1992-11
- Volume
- 4
- Issue
- 6
- Pages
- 863-879
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W1994618660
- Cited by
- 264
- References
- 14
- FWCI
- 4.92
- 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.