Neural Modularity Helps Organisms Evolve to Learn New Skills without Forgetting Old Skills
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
A long-standing goal in artificial intelligence is creating agents that can learn a variety of different skills for different problems. In the artificial intelligence subfield of neural networks, a barrier to that goal is that when agents learn a new skill they typically do so by losing previously acquired skills, a problem called catastrophic forgetting. That occurs because, to learn the new task, neural learning algorithms change connections that encode previously acquired skills. How networks are organized critically affects their learning dynamics. In this paper, we test whether catastrophic forgetting can be reduced by evolving modular neural networks. Modularity intuitively should reduce learning interference between tasks by separating functionality into physically distinct modules in which learning can be selectively turned on or off. Modularity can further improve learning by having a reinforcement learning module separate from sensory processing modules, allowing learning to happen only in response to a positive or negative reward. In this paper, learning takes place via neuromodulation, which allows agents to selectively change the rate of learning for each neural connection based on environmental stimuli (e.g. to alter learning in specific locations based on the task at hand). To produce modularity, we evolve neural networks with a cost for neural connections. We show that this connection cost technique causes modularity, confirming a previous result, and that such sparsely connected, modular networks have higher overall performance because they learn new skills faster while retaining old skills more and because they have a separate reinforcement learning module. Our results suggest (1) that encouraging modularity in neural networks may help us overcome the long-standing barrier of networks that cannot learn new skills without forgetting old ones, and (2) that one benefit of the modularity ubiquitous in the brains of natural animals might be to alleviate the problem of catastrophic forgetting.
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
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Modularity and community structure in networks
Newman, M. E. J. (2006) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0601602103 · Cited by 12,256
Fortunato, S. (2010) · Physics Reports · doi:10.1016/j.physrep.2009.11.002 · Cited by 11,293 · cited 1×
“Here we applied the spectral optimization method , which gives good results in practice at a low computational cost [67, 78].”
MethodLearning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 9,239
McClelland, J. L., McNaughton, B. L., & O'Reilly, R. C. (1995) · Psychological Review · doi:10.1037/0033-295x.102.3.419 · Cited by 5,256 · cited 1×
“Dual-net architectures, on the other hand, present a biologically plausible [35] mechanism for limiting catastrophic forgetting [33, 36].”
BackgroundCatastrophic Interference in Connectionist Networks: The Sequential Learning Problem
McCloskey, M., & Cohen, N. J. (1989) · Psychology of Learning and Motivation · doi:10.1016/s0079-7421(08)60536-8 · Cited by 3,770
An Introduction to Systems Biology: Design Principles of Biological Circuits
Alon, U. (2006) · doi:10.1201/9781420011432 · Cited by 2,825
Catastrophic forgetting in connectionist networks
French, R. (1999) · Trends in Cognitive Sciences · doi:10.1016/s1364-6613(99)01294-2 · Cited by 2,311
Abbott, L. F., & Regehr, W. G. (2004) · Nature · doi:10.1038/nature03010 · Cited by 1,684
An Introduction to Systems Biology: Design Principles of Biological Circuits
Alon, U. (2019) · doi:10.1201/9780429283321 · Cited by 955
Ratcliff, R. (1990) · Psychological Review · doi:10.1037//0033-295x.97.2.285 · Cited by 941
Modularity from fluctuations in random graphs and complex networks
Guimerà, R., Sales-Pardo, M., & Amaral, L. A. N. (2004) · Physical Review E · doi:10.1103/physreve.70.025101 · Cited by 894
Catastrophic forgetting, rehearsal and pseudorehearsal
ROBINS, A. (1995) · Connection Science · doi:10.1080/09540099550039318 · Cited by 833 · cited 1×
“Interleaved learning avoids catastrophic forgetting by training on both old and new data when learning [10], although this method cannot scale and does not work for realistic environments because in the real world not all challenges are faced concurrently [33, 34].”
BackgroundWiring cost in the organization of a biological neuronal network
Ahn, Y.-Y., Jeong, H., & Kim, B. J. (2006) · Physica A: Statistical Mechanics and its Applications · doi:10.1016/j.physa.2005.12.013 · Cited by 69 · cited 1×
“to build connections, maintain them, and house them) and there is evidence that natural selection optimally arranges neurons to minimize these connection costs [26, 27].”
Background
Cited by
Sporns, O., & Betzel, R. F. (2016) · Annual Review of Psychology · doi:10.1146/annurev-psych-122414-033634 · Cited by 1,334
Designing neural networks through neuroevolution
Stanley, K. O., Clune, J., Lehman, J., & Miikkulainen, R. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-018-0006-z · Cited by 689
Self-citationNEMO: cancer subtyping by integration of partial multi-omic data
Rappoport, N., & Shamir, R. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz058 · Cited by 286
Biological underpinnings for lifelong learning machines
Kudithipudi, D., Aguilar-Simon, M., Babb, J., Bazhenov, M., Blackiston, D., Bongard, J., Brna, A. P., Chakravarthi Raja, S., Cheney, N., Clune, J., et al. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00452-0 · Cited by 236
Self-citationGo-Explore: a New Approach for Hard-Exploration Problems
Ecoffet, A., Huizinga, J., Lehman, J., Stanley, K. O., & Clune, J. (2019) · arXiv · doi:10.48550/arxiv.1901.10995 · Cited by 205
“It likely would also have no implicit memory of this frontier due to the problem of catastrophic forgetting [17–20].”
BackgroundSelf-citation
Metadata
- Authors
- Ellefsen, K. O., Mouret, J.-B., & Clune, J.
- Venue
- PLOS Computational Biology
- Publisher
- Public Library of Science (PLoS)
- Published
- 2015-04-02
- Volume
- 11
- Issue
- 4
- Pages
- e1004128
- ISSN
- 1553-734X (ISSN-L)
- 1553-7358
- OpenAlex
- W2082582863
- Cited by
- 151
- References
- 14
- FWCI
- 15.33
- 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.