The Evolution of Representation in Simple Cognitive Networks
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Representations are internal models of the environment that can provide guidance to a behaving agent, even in the absence of sensory information. It is not clear how representations are developed and whether they are necessary or even essential for intelligent behavior. We argue here that the ability to represent relevant features of the environment is the expected consequence of an adaptive process, give a formal definition of representation based on information theory, and quantify it with a measure R. To measure how R changes over time, we evolve two types of networks—an artificial neural network and a network of hidden Markov gates—to solve a categorization task using a genetic algorithm. We find that the capacity to represent increases during evolutionary adaptation and that agents form representations of their environment during their lifetime. This ability allows the agents to act on sensorial inputs in the context of their acquired representations and enables complex and context-dependent behavior. We examine which concepts (features of the environment) our networks are representing, how the representations are logically encoded in the networks, and how they form as an agent behaves to solve a task. We conclude that R should be able to quantify the representations within any cognitive system and should be predictive of an agent's long-term adaptive success.
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
Intelligence without representation
Brooks, R. A. (1991) · Artificial Intelligence · doi:10.1016/0004-3702(91)90053-m · Cited by 4,853
Hierarchical models of object recognition in cortex
Riesenhuber, M., & Poggio, T. (1999) · Nature Neuroscience · doi:10.1038/14819 · Cited by 3,309 · cited 1×
“e.g., Koller and Friedman 2009) and are related to the hierarchical temporal memory model of neocortical function (Hawkins and Blakeslee, 2004; George and Hawkins, 2005, 2009) and the HMAX algorithm (Riesenhuber and Poggio, 1999), except that Markov brains need not be organized in a strictly hierarchical manner as the…”
BackgroundInternal models for motor control and trajectory planning.
Kawato, M. (1999) · Current Opinion in Neurobiology · doi:10.1016/s0959-4388(99)00028-8 · Cited by 2,685 · cited 1×
“We believe that the reason for the lack of progress does not lie in the attempt to base AI research in mobile autonomous robots, but that instead representations (also sometimes called “internal models”, (Craik, 1943; Wolpert et al., 1995; Kawato, 1999)) are key to complex adaptive behavior.”
BackgroundInfluentialConsciousness as integrated information: a provisional manifesto
Tononi, G. (2008) · The Biological Bulletin · doi:10.2307/25470707 · Cited by 1,529
Resilient Machines Through Continuous Self-Modeling
Bongard, J., Zykov, V., & Lipson, H. (2006) · Science · doi:10.1126/science.1133687 · Cited by 709 · cited 1×
“Representations can be updated during the lifetime or over the course of evolution and thus are able to handle even new sensory input (Bongard et al., 2006).”
BackgroundCould information theory provide an ecological theory of sensory processing?
Atick, J. J. (2011) · Network: Computation in Neural Systems · doi:10.3109/0954898x.2011.638888 · Cited by 679
Statistically optimal perception and learning: from behavior to neural representations
Fiser, J., Berkes, P., Orbán, G., & Lengyel, M. (2010) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2010.01.003 · Cited by 672 · cited 1×
“terms of the language of Bayesian inference, the network’s representations can be understood as priors that reflect the relevant statistical distribution of the environment (Kording and Wolpert, 2004; Fiser et al., 2010; Thornton, 2009). We thus conclude that the network properties that Rmeasures are indeed representat…”
BackgroundIntegrated information in discrete dynamical systems: motivation and theoretical framework
Balduzzi, D., & Tononi, G. (2008) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1000091 · Cited by 419 · cited 2×
“SIatom is a special case of the information integration measure Φ (Tononi, 2008; Balduzzi and Tononi, 2008), which is computationally far more complex than SIatom because it relies on computing information integration across all possible partitions of a network.”
BackgroundTowards a mathematical theory of cortical micro-circuits
George, D., & Hawkins, J. (2009) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1000532 · Cited by 404
The philosophical novelty of computer simulation methods
Humphreys, P. (2009) · Synthese · doi:10.1007/s11229-008-9435-2 · Cited by 362
Cited by
Albantakis, L., Hintze, A., Koch, C., Adami, C., & Tononi, G. (2014) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1003966 · Cited by 101
Albantakis, L., & Tononi, G. (2015) · Entropy · doi:10.3390/e17085472 · Cited by 58
“The probability of an animat to be selected into the next generation was proportional to an exponential measure of the animat’s fitness (roulette wheel selection) [19,33].”
BackgroundGulson, K. N., & Webb, P. T. (2017) · Research in Education · doi:10.1177/0034523717723385 · Cited by 55
“Any form of governance that uses forms of data-driven and data-based reasoning, including machine learning, will be reliant upon representation, modelling and simulation (Marstaller et al., 2013).”
BackgroundCausal composition: Structural differences among dynamically equivalent systems
Albantakis, L., & Tononi, G. (2019) · Entropy · doi:10.3390/e21100989 · Cited by 30
“This is demonstrated particularly well by recent computational studies involving simulated artificial agents with minimal cognitive architectures [15,23,68,69], whose behavior can easily be predicted.”
BackgroundA Tale of Two Animats: What does it take to have goals?
Albantakis, L. (2017) · arXiv · doi:10.48550/arxiv.1705.10854 · Cited by 13
“Fifty independent populations of adaptive Markov Brains, each starting from a different pseudo-random seed, were released into a digital world full of dangers and rewards.”
BackgroundMethodInfluential
Metadata
- Authors
- Marstaller, L., Hintze, A., & Adami, C.
- Venue
- Neural Computation
- Publisher
- MIT Press
- Published
- 2013-08
- Volume
- 25
- Issue
- 8
- Pages
- 2079-2107
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W2166110729
- Cited by
- 70
- References
- 10
- FWCI
- 6.63
- Type
- journal article
- Language
- en
- Open access
- green
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.