Feature Extraction Through LOCOCODE
The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
Low-complexity coding and decoding (LOCOCODE) is a novel approach to sensory coding and unsupervised learning. Unlike previous methods, it explicitly takes into account the information-theoretic complexity of the code generator. It computes lococodes that convey information about the input data and can be computed and decoded by low-complexity mappings. We implement LOCOCODE by training autoassociators with flat minimum search, a recent, general method for discovering low-complexity neural nets. It turns out that this approach can unmix an unknown number of independent data sources by extracting a minimal number of low-complexity features necessary for representing the data. Experiments show that unlike codes obtained with standard autoencoders, lococodes are based on feature detectors, never unstructured, usually sparse, and sometimes factorial or local (depending on statistical properties of the data). Although LOCOCODE is not explicitly designed to enforce sparse or factorial codes, it extracts optimal codes for difficult versions of the “bars” benchmark problem, whereas independent component analysis (ICA) and principal component analysis (PCA) do not. It produces familiar, biologically plausible feature detectors when applied to real-world images and codes with fewer bits per pixel than ICA and PCA. Unlike ICA, it does not need to know the number of independent sources. As a preprocessor for a vowel recognition benchmark problem, it sets the stage for excellent classification performance. Our results reveal an interesting, previously ignored connection between two important fields: regularizer research and ICA-related research. They may represent a first step toward unification of regularization and unsupervised learning.
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
Self-Organization and Associative Memory
Kohonen, T. (1989) · Springer Series in Information Sciences · doi:10.1007/978-3-642-88163-3 · Cited by 8,740
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 6×
“Unlike previous approaches, it does not depend on explicit terms enforcing independence (e.g., Schmidhuber, 1992), zero mutual information among code components (e.g., Linsker, 1988; Deco & Parra, 1994), or sparseness (e.g., Field, 1994; Zemel & Hinton, 1994; Olshausen & Field, 1996; Zemel, 1993; Hinton & Ghahramani,…”
BackgroundMethodInfluentialNonlinear principal component analysis using autoassociative neural networks
Kramer, M. A. (1991) · AIChE Journal · doi:10.1002/aic.690370209 · Cited by 3,037
A formal theory of inductive inference. Part II
Solomonoff, R. J. (1964) · Information and Control · doi:10.1016/s0019-9958(64)90131-7 · Cited by 1,758
Neural networks and principal component analysis: Learning from examples without local minima
Baldi, P., & Hornik, K. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90014-2 · Cited by 1,383 · cited 1×
“Baldi and Hornik (1989) studied linear AAs with a hidden-layer bottleneck and found that their codes are orthogonal projections onto the subspace spanned by the first principal eigenvectors of a covariance matrix associated with the training patterns.”
BackgroundA formal theory of inductive inference. Part I
Solomonoff, R. J. (1964) · Information and Control · doi:10.1016/s0019-9958(64)90223-2 · Cited by 1,192
The "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
Separation of a mixture of independent signals using time delayed correlations
Molgedey, L., & Schuster, H. G. (1994) · Physical Review Letters · doi:10.1103/physrevlett.72.3634 · Cited by 882 · cited 1×
“In sections 4.3 and 4.4 we compare LOCOCODE to simple variants of ICA (e.g., Jutten & Herault, 1991; Cardoso & Souloumiac, 1993; Molgedey & Schuster, 1994; Comon, 1994; Bell & Sejnowski, 1995; Amari, Cichocki, & Yang, 1996; Nadal & Parga, 1997) and PCA (e.g., Oja, 1989).”
Influential
Cited by
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-citationFast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
Clevert, D.-A., Unterthiner, T., & Hochreiter, S. (2015) · arXiv · doi:10.48550/arxiv.1511.07289 · Cited by 4,513
“Therefore the representation is both noise-robust and low-complex (Hochreiter & Schmidhuber, 1999).”
BackgroundSelf-citationLee, T.-W., Girolami, M., & Sejnowski, T. J. (1999) · Neural Computation · doi:10.1162/089976699300016719 · Cited by 1,967
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-citationIndependent Component Analysis: Principles and Practice
(2001) · Cambridge University Press eBooks · doi:10.1017/cbo9780511624148 · Cited by 1,917
Metadata
- Authors
- Hochreiter, S., & Schmidhuber, J.
- Venue
- Neural Computation
- Publisher
- MIT Press - Journals
- Published
- 1999-04-01
- Volume
- 11
- Issue
- 3
- Pages
- 679-714
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W2061209832
- Cited by
- 83
- References
- 8
- FWCI
- 12.21
- 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.