Comparing Information-Theoretic Measures of Complexity in Boltzmann Machines
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
In the past three decades, many theoretical measures of complexity have been proposed to help understand complex systems. In this work, for the first time, we place these measures on a level playing field, to explore the qualitative similarities and differences between them, and their shortcomings. Specifically, using the Boltzmann machine architecture (a fully connected recurrent neural network) with uniformly distributed weights as our model of study, we numerically measure how complexity changes as a function of network dynamics and network parameters. We apply an extension of one such information-theoretic measure of complexity to understand incremental Hebbian learning in Hopfield networks, a fully recurrent architecture model of autoassociative memory. In the course of Hebbian learning, the total information flow reflects a natural upward trend in complexity as the network attempts to learn more and more patterns.
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
Mitchell, M. (2009) · doi:10.1093/oso/9780195124415.001.0001 · Cited by 2,310
Tononi, G., Sporns, O., & Edelman, G. M. (1994) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.91.11.5033 · Cited by 1,626 · cited 1×
“, first proposed in [6] and most recently refined in [7], as a measure of consciousness, as well as similar measures of integrated information described by Barrett & Seth [8], and Oizumi et al.”
MethodFrom the phenomenology to the mechanisms of consciousness: integrated information theory 3.0
Oizumi, M., Albantakis, L., & Tononi, G. (2014) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1003588 · Cited by 1,128
Practical Measures of Integrated Information for Time-Series Data
Barrett, A. B., & Seth, A. K. (2011) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1001052 · Cited by 225 · cited 2×
“Additional notable information-theoretic measures that we do not examine include those of Tononi et al., first proposed in [6] and most recently refined in [7], as a measure of consciousness, as well as similar measures of integrated information described by Barrett & Seth [8], and Oizumi et al. [9].”
MethodMeasuring Integrated Information from the Decoding Perspective
Oizumi, M., Amari, S.-I., Yanagawa, T., Fujii, N., & Tsuchiya, N. (2016) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1004654 · Cited by 184
Cited by
Measuring integrated information: comparison of candidate measures in theory and simulation
Mediano, P., Seth, A., & Barrett, A. (2018) · Entropy · doi:10.3390/e21010017 · Cited by 145
Degeneracy and Redundancy in Active Inference
Sajid, N., Parr, T., Hope, T. M., Price, C. J., & Friston, K. J. (2020) · Cerebral Cortex · doi:10.1093/cercor/bhaa148 · Cited by 49
Science-Driven Societal Transformation, Part I: Worldview
(2020) · doi:10.3390/su12176881 · Cited by 13
Integrated information as a measure of cognitive processes in coupled genetic repressilators
Abrego, L., & Zaikin, A. (2019) · Entropy · doi:10.3390/e21040382 · Cited by 5
Metadata
- Authors
- Kanwal, M., Grochow, J., & Ay, N.
- Venue
- Entropy
- Publisher
- MDPI AG
- Published
- 2017-07-03
- Volume
- 19
- Issue
- 7
- Pages
- 310
- ISSN
- 1099-4300 (ISSN-L)
- OpenAlex
- W2727563815
- Cited by
- 19
- References
- 5
- FWCI
- 1.97
- Type
- journal article
- Language
- en
- Open access
- gold
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.