Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes
The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
I argue that data becomes temporarily interesting by itself to some self-improving, but computationally limited, subjective observer once he learns to predict or compress the data in a better way, thus making it subjectively simpler and more beautiful. Curiosity is the desire to create or discover more non-random, non-arbitrary, regular data that is novel and surprising not in the traditional sense of Boltzmann and Shannon but in the sense that it allows for compression progress because its regularity was not yet known. This drive maximizes interestingness, the first derivative of subjective beauty or compressibility, that is, the steepness of the learning curve. It motivates exploring infants, pure mathematicians, composers, artists, dancers, comedians, yourself, and (since 1990) artificial systems.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Self-citationNeural Networks for Pattern Recognition
Bishop, C. M. (1995) · doi:10.1093/oso/9780198538493.001.0001 · Cited by 12,287
Reinforcement Learning: A Survey
Kaelbling, L. P., Littman, M. L., & Moore, A. W. (1996) · Journal of Artificial Intelligence Research · doi:10.1613/jair.301 · Cited by 8,972
On computable numbers, with an application to the entscheidungsproblem
Turing, A. M. (1937) · Proceedings of the London Mathematical Society · doi:10.1112/plms/s2-42.1.230 · Cited by 8,283
PINKER, S. (1999) · Annals of the New York Academy of Sciences · doi:10.1111/j.1749-6632.1999.tb08538.x · Cited by 3,738
Über formal unentscheidbare Sätze der Principia Mathematica und verwandter Systeme I
Gödel, K. (1931) · Monatshefte für Mathematik und Physik · doi:10.1007/bf01700692 · Cited by 2,395
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
Information-based objective functions for active data selection
MacKay, D. J. C. (1992) · Neural Computation · doi:10.1162/neco.1992.4.4.590 · Cited by 1,221
A 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
Sims, K. (1994) · Proceedings of the 21st annual conference on Computer graphics and interactive techniques - SIGGRAPH '94 · doi:10.1145/192161.192167 · Cited by 1,005 · cited 1×
“Many approaches to evolving RNN have been proposed [40, 122, 121, 45, 39, 103, 42].”
BackgroundUniversal Artificial Intellegence
Hutter, M. (2005) · Texts in Theoretical Computer Science An EATCS Series · doi:10.1007/b138233 · Cited by 523 · cited 7×
“Its computable variant AIXI(t,l) [ 23 ] has asymptotically optimal runtime but may suffer from a huge constant slowdown.”
BackgroundMethodInfluentialArtificial General Intelligence
(2007) · Cognitive Technologies · doi:10.1007/978-3-540-68677-4 · Cited by 473
Gödel Machines: Fully Self-referential Optimal Universal Self-improvers
Schmidhuber, J. (2007) · Cognitive Technologies · doi:10.1007/978-3-540-68677-4_7 · Cited by 110
Self-citationSchmidhuber, J. (2003) · Natural Computing Series · doi:10.1007/978-3-642-18965-4_23 · Cited by 65
Self-citationSchmidhuber, J. (2003) · arXiv · doi:10.48550/arxiv.cs/0309048 · Cited by 24
Self-citation
Cited by
Formal theory of creativity, fun, and intrinsic motivation (1990–2010)
Schmidhuber, J. (2010) · IEEE Transactions on Autonomous Mental Development · doi:10.1109/tamd.2010.2056368 · Cited by 747
“They embody approximations of a simple, but general, formal theory of creativity and curiosity and inte restingness and fun, explaining essential aspects of human or no nhuman intelligence, including selective attention, scien e, art, music, humor [85], [92], [97], [96], [94].”
BackgroundMethodInfluentialSelf-citationOn scientific understanding with artificial intelligence
Krenn, M., Pollice, R., Guo, S. Y., Aldeghi, M., Cervera-Lierta, A., Friederich, P., dos Passos Gomes, G., Häse, F., Jinich, A., Nigam, A., et al. (2022) · Nature Reviews Physics · doi:10.1038/s42254-022-00518-3 · Cited by 372
Towards Continual Reinforcement Learning: A Review and Perspectives
Khetarpal, K., Riemer, M., Rish, I., & Precup, D. (2020) · arXiv · doi:10.48550/arxiv.2012.13490 · Cited by 227
Towards Continual Reinforcement Learning: A Review and Perspectives
Khetarpal, K., Riemer, M., Rish, I., & Precup, D. (2022) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.13673 · Cited by 224
Lessons from infant learning for unsupervised machine learning
Zaadnoordijk, L., Besold, T. R., & Cusack, R. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00488-2 · Cited by 65
“195 argued that curiosity-driven learning occurs most optimally when the agent seeks out information as a function of its compressibility.”
Background
Metadata
- Authors
- Schmidhuber, J.
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Berlin Heidelberg
- Published
- 2009
- Pages
- 48-76
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W1680245855
- Cited by
- 139
- References
- 15
- FWCI
- 10.40
- Type
- conference paper
- 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.