Corpus ID: 162184038

Cognitive Model Priors for Predicting Human Decisions

@article{Bourgin2019CognitiveMP,
  title={Cognitive Model Priors for Predicting Human Decisions},
  author={David D. Bourgin and Joshua C. Peterson and Daniel Reichman and Thomas L. Griffiths and Stuart J. Russell},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.09397}
}
Human decision-making underlies all economic behavior. [...] Key Method We offer two contributions towards this end: first, we construct "cognitive model priors" by pretraining neural networks with synthetic data generated by cognitive models (i.e., theoretical models developed by cognitive psychologists). We find that fine-tuning these networks on small datasets of real human decisions results in unprecedented state-of-the-art improvements on two benchmark datasets. Second, we present the first large-scale…Expand
PsychFM: Predicting your next gamble
TLDR
A novel hybrid model namely psychological factorisation machine ( PsychFM) has been proposed that involves concepts from machine learning as well as psychological theories and outperforms the popular existing models namely random forest and factorisation machines for the benchmark dataset CPC-18. Expand
Cognitive science as a source of forward and inverse models of human decisions for robotics and control
  • Mark K. Ho, T. Griffiths
  • Computer Science, Engineering
  • ArXiv
  • 2021
TLDR
relevant recent developments are highlighted, including approaches that synthesize blackbox and theory-driven modeling, accounts that recast heuristics and biases as forms of bounded optimality, and models that characterize human theory of mind and communication in decision-theoretic terms. Expand
Scaling up Psychology via Scientific Regret Minimization: A Case Study in Moral Decision-Making
TLDR
It is found that incorporating a set of deontological principles that capture dimensions along which groups of agents can vary improves a computational model of human moral judgment, and three interesting moral phenomena are identified and independently validated. Expand
REGRET MINIMIZATION 3 Scaling up Psychology via Scientific Regret Minimization : A Case Study in Moral Decisions
Do large datasets provide value to psychologists? Without a systematic methodology for working with such datasets, there is a valid concern that exploratory analyses will produce noise artifactsExpand
Learning Representations by Humans, for Humans
TLDR
A new, complementary approach to interpretability is proposed, in which machines are not considered as experts whose role it is to suggest what should be done and why, but rather as advisers that are effective for human decision-making. Expand
Using Cognitive Models to Train Big Data Models with Small Data
TLDR
This work shows a novel and general method of generating copious synthetic data of human behavior using a cognitive architecture, and then uses the data to train a deep network classifier to predict ensuing human actions. Expand
Limits on Predictability of Risky Choice Behavior
TLDR
It is argued that the level of precision attained by recent choice models is unexpected, because human preferences are irreducibly noisy, and choice models for decisions from description are significantly more consistent with humans’ choices than humans themselves are consistent with their own choices. Expand
A neural network walks into a lab: towards using deep nets as models for human behavior
TLDR
It is argued that methods for assessing the goodness of fit between DNN models and human behavior have to date been impoverished, and cognitive science might have to start using more complex tasks, but doing so might be beneficial for DNN-independent reasons as well. Expand
Scaling up psychology via Scientific Regret Minimization
TLDR
An exploratory approach that combines ideas from machine learning and psychology is offered, and it is found that incorporating a set of deontological principles that capture dimensions along which groups of agents can vary improves a computational model of human moral judgment. Expand
TUTOR: Training Neural Networks Using Decision Rules as Model Priors
TLDR
TUTOR is a less data-hungry, accurate, and efficient DNN synthesis framework that synthesizes accurate DNN models with limited available data, and reduced memory and computational requirements. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 29 REFERENCES
Behavior-Based Machine-Learning: A Hybrid Approach for Predicting Human Decision Making
TLDR
A vanilla model is implemented in which SVM models are trained using behavioral features that rely on the psychological properties underlying the competition baseline model, and it is shown that this basic model captures the 14 choice biases and outperforms all the other learning-based models in the competition. Expand
Predicting human decisions with behavioral theories and machine learning
TLDR
An open tournament for prediction of human choices in fundamental economic decision tasks is presented and it is suggested that integration of certain behavioral theories as features in machine learning systems provides the best predictions. Expand
Using Methods from Machine Learning to Evaluate Behavioral Models of Choice Under Risk and Ambiguity
How can behavioral scientists incorporate tools from machine learning (ML)? We propose that ML models can be used as upper bounds for the “explainable” variance in a given data set and thus serve asExpand
Deep Learning for Predicting Human Strategic Behavior
TLDR
This work introduces a novel architecture that allows a single network to generalize across different input and output dimensions by using matrix units rather than scalar units, and shows that its performance significantly outperforms that of the previous state of the art, which relies on expert-constructed features. Expand
Choosing Prediction Over Explanation in Psychology: Lessons From Machine Learning
  • T. Yarkoni, Jacob Westfall
  • Psychology, Medicine
  • Perspectives on psychological science : a journal of the Association for Psychological Science
  • 2017
TLDR
It is proposed that principles and techniques from the field of machine learning can help psychology become a more predictive science and an increased focus on prediction, rather than explanation, can ultimately lead to greater understanding of behavior. Expand
The Theory is Predictive, but is it Complete?: An Application to Human Perception of Randomness
TLDR
Overall, the results indicate that (i) there is a significant amount of structure in this problem that existing models have yet to capture and (ii) there are rich domains in which machine learning may provide a viable approach to testing completeness. Expand
From Anomalies to Forecasts: Toward a Descriptive Model of Decisions Under Risk, Under Ambiguity, and From Experience
TLDR
This article analyzes 14 choice anomalies that have been described by different models, including the Allais, St. Petersburg, and Ellsberg paradoxes, and uses a choice prediction competition methodology to clarify the interaction between the different anomalies. Expand
Psychological Forest: Predicting Human Behavior
TLDR
A random forest algorithm, dubbed psychological forest, is presented, which makes use of the psychological features in addition to the more standard objective and naive features, leads to prediction that significantly outperforms best practices in a choice prediction competition. Expand
Machine Learning: An Applied Econometric Approach
TLDR
This work presents a way of thinking about machine learning that gives it its own place in the econometric toolbox, and aims to make them conceptually easier to use by providing a crisper understanding of how these algorithms work, where they excel, and where they can stumble. Expand
Predicting Human Decision-Making: From Prediction to Action
TLDR
This talk will show how combining machine learning techniques for human modeling, human behavioral models, formal decision-making and game theory approaches enables agents to interact well with people. Expand
...
1
2
3
...