A neuro-vector-symbolic architecture for solving Raven’s progressive matrices
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Neuro-symbolic artificial intelligence approaches display both perception and reasoning capabilities, but inherit the limitations of their individual deep learning and symbolic artificial intelligence components. By combining neural networks and vector-symbolic architectures, Hersche and colleagues propose a neuro-vector-symbolic framework that can solve Raven’s progressive matrices tests faster and more accurately than other state-of-the-art methods. Neither deep neural networks nor symbolic artificial intelligence (AI) alone has approached the kind of intelligence expressed in humans. This is mainly because neural networks are not able to decompose joint representations to obtain distinct objects (the so-called binding problem), while symbolic AI suffers from exhaustive rule searches, among other problems. These two problems are still pronounced in neuro-symbolic AI, which aims to combine the best of the two paradigms. Here we show that the two problems can be addressed with our proposed neuro-vector-symbolic architecture (NVSA) by exploiting its powerful operators on high-dimensional distributed representations that serve as a common language between neural networks and symbolic AI. The efficacy of NVSA is demonstrated by solving Raven’s progressive matrices datasets. Compared with state-of-the-art deep neural network and neuro-symbolic approaches, end-to-end training of NVSA achieves a new record of 87.7% average accuracy in RAVEN, and 88.1% in I-RAVEN datasets. Moreover, compared with the symbolic reasoning within the neuro-symbolic approaches, the probabilistic reasoning of NVSA with less expensive operations on the distributed representations is two orders of magnitude faster.
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
Connectionism and cognitive architecture: A critical analysis
Fodor, J. A., & Pylyshyn, Z. W. (1988) · Cognition · doi:10.1016/0010-0277(88)90031-5 · Cited by 4,022
PRINCIPLES OF NEURODYNAMICS. PERCEPTRONS AND THE THEORY OF BRAIN MECHANISMS
ROSENBLATT, F. (1961) · doi:10.21236/ad0256582 · Cited by 1,691
Carpenter, P. A., Just, M. A., & Shell, P. (1990) · Psychological Review · doi:10.1037/0033-295x.97.3.404 · Cited by 1,648
Simple statistical gradient-following algorithms for connectionist reinforcement learning
Williams, R. J. (1992) · Machine Learning · doi:10.1023/a:1022672621406 · Cited by 817
Holographic reduced representations
Plate, T. A. (1995) · IEEE Transactions on Neural Networks · doi:10.1109/72.377968 · Cited by 657
von der Malsburg, C. (1999) · Neuron · doi:10.1016/s0896-6273(00)80825-9 · Cited by 501
Mao, J., Gan, C., Kohli, P., Tenenbaum, J. B., & Wu, J. (2019) · arXiv · doi:10.48550/arxiv.1904.12584 · Cited by 444
The Algebraic Mind: Integrating Connectionism and Cognitive Science
Marcus, G. F. (2001) · doi:10.7551/mitpress/1187.001.0001 · Cited by 341
CHALMERS, D. J., FRENCH, R. M., & HOFSTADTER, D. R. (1992) · Journal of Experimental & Theoretical Artificial Intelligence · doi:10.1080/09528139208953747 · Cited by 333
In-memory hyperdimensional computing
Karunaratne, G., Le Gallo, M., Cherubini, G., Benini, L., Rahimi, A., & Sebastian, A. (2020) · Nature Electronics · doi:10.1038/s41928-020-0410-3 · Cited by 293
Self-citation
Cited by
Emergent analogical reasoning in large language models
Webb, T., Holyoak, K. J., & Lu, H. (2023) · Nature Human Behaviour · doi:10.1038/s41562-023-01659-w · Cited by 404
Constrained Few-shot Class-incremental Learning
Hersche, M., Karunaratne, G., Cherubini, G., Benini, L., Sebastian, A., & Rahimi, A. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00885 · Cited by 167
Self-citationKleyko, D., Rachkovskij, D., Osipov, E., & Rahimi, A. (2023) · ACM Computing Surveys · doi:10.1145/3558000 · Cited by 141
Self-citationTowards Cognitive AI Systems: Workload and Characterization of Neuro-Symbolic AI
Wan, Z., Liu, C.-K., Yang, H., Raj, R., Li, C., You, H., Fu, Y., Wan, C., Samajdar, A., Lin, Y. C., et al. (2024) · 2024 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) · doi:10.1109/ispass61541.2024.00033 · Cited by 39
Metadata
- Authors
- Hersche, M., Zeqiri, M., Benini, L., Sebastian, A., & Rahimi, A.
- Venue
- Nature Machine Intelligence
- Published
- 2023-03-09
- Volume
- 5
- Issue
- 4
- Pages
- 363-375
- ISSN
- 2522-5839 (ISSN-L)
- OpenAlex
- W4360977202
- Cited by
- 81
- References
- 13
- FWCI
- 6.68
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: A neuro-vector-symbolic architecture for solving Raven’s progressive matrices. https://app.cochat.ai/papers/10.1038/s42256-023-00630-8
- The paper
- Hersche, M., Zeqiri, M., Benini, L., Sebastian, A., & Rahimi, A. (2023). A neuro-vector-symbolic architecture for solving Raven’s progressive matrices. Nature Machine Intelligence. https://doi.org/10.1038/s42256-023-00630-8
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.