Predictive and Interpretable: Combining Artificial Neural Networks and Classic Cognitive Models to Understand Human Learning and Decision Making
Open accessAbstract
Quantitative models of behavior are a fundamental tool in cognitive science. Typically, models are hand-crafted to implement specific cognitive mechanisms. Such “classic” models are interpretable by design, but may provide poor fit to experimental data. Artificial neural networks (ANNs), on the contrary, can fit arbitrary datasets at the cost of opaque mechanisms. Here, we adopt a hybrid approach, combining the predictive power of ANNs with the interpretability of classic models. We apply this approach to Reinforcement Learning (RL), beginning with classic RL models and replacing their components one-by-one with ANNs. We find that hybrid models can provide similar fit to fully-general ANNs, while retaining the interpretability of classic cognitive models: They reveal reward-based learning mechanisms in humans that are strikingly similar to classic RL. They also reveal mechanisms not contained in classic models, including separate rewardblind mechanisms, and the specific memory contents relevant to reward-based and reward-blind mechanisms.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
ANNs can learn complex mappings from data, vastly expanding the space of candidate functions that can be considered.
“ANNs can learn complex mappings from data, vastly expanding the space of candidate functions that can be considered (Fig. 1b, bottom)15,16.”
From Interpretable abstractions of artificial neural networks predict behavior and neural activity during human information gathering (2026) · cites this paper as [15]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 37 · Cited by 18
Research works printed but not linked: 9
- Busemeyer, J. R., & Diederich, A. (2010). Cognitive Model- ing. Sage Publications, Incorporated.
- Dezfouli, A., Ashtiani, H., Ghattas, O., Nock, R., Dayan, P., & Ong, C. S. (2019). Disentangled behavioural representa- tions. Advances in Neural Information Processing Systems, 32.
- Kuperwajs, I., Schuett, H., & Ma, W. J. (2022). Improving a model of human planning via large-scale data and deep neural networks. Proceedings of the Annual Meeting of the Cognitive Science Society, 44(44).
- Ma, W. J., & Peters, B. (2020). A neural network walks into a lab: Towards using deep nets as models for human behav- ior (tech. rep. arXiv:2005.02181) [arXiv:2005.02181 [cs, q-bio] type: article]. arXiv. · arXiv
- Noti, G., Levi, E., Kolumbus, Y., & Daniely, A. (2016). Behavior-Based Machine-Learning: A Hybrid Approach for Predicting Human Decision Making [arXiv:1611.10228 · arXiv
- Palminteri, S., Khamassi, M., Joffily, M., & Coricelli, G. (2015). Contextual modulation of value signals in reward and punishment learning [Number: 1 Publisher: Nature Publishing Group]. Nature Communications, 6(1), 8096.
- Palminteri, S., Wyart, V., & Koechlin, E. (2017). The Impor- tance of Falsification in Computational Cognitive Model- ing. Trends in Cognitive Sciences, 21(6), 425-433.
- Sugawara, M., & Katahira, K. (2021). Dissociation between asymmetric value updating and perseverance in human re- inforcement learning [Number: 1 Publisher: Nature Pub- lishing Group]. Scientific Reports, 11(1), 3574.
- Sutton, R. S., & Barto, A. G. (2017). Reinforcement Learn- ing: An Introduction (2nd ed.). MIT Press.
- Authors
- Eckstein, M. K., Summerfield, C., Daw, N. D., & Miller, K. J.
- Affiliations
- Google DeepMind (United Kingdom) (GB)
- Corresponding author
- Eckstein, Maria K.
- Venue
- bioRxiv (Cold Spring Harbor Laboratory)
- Publisher
- openRxiv
- Published
- 2023-05-17
- OpenAlex
- W4377024110
- Cited by
- 18
- References
- 37
- Citations by year
- 2026: 4 · 2025: 6 · 2024: 4 · 2023: 4
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Licence
- cc-by-nc
- Locations
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc)
- eScholarship (California Digital Library) (submittedVersion, cc-by)
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › Neural and Behavioral Psychology Studies
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Social Sciences › Decision Sciences › General Decision Sciences › Decision-Making and Behavioral Economics
- Keywords
- hybrid model, artificial neural networks, interpretability, reinforcement learning, human learning, decision-making, reward learning, memory content
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
