Timezone: »

 
Poster
Disentangled behavioural representations
Amir Dezfouli · Hassan Ashtiani · Omar Ghattas · Richard Nock · Peter Dayan · Cheng Soon Ong

Wed Dec 11 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #141

Individual characteristics in human decision-making are often quantified by fitting a parametric cognitive model to subjects' behavior and then studying differences between them in the associated parameter space. However, these models often fit behavior more poorly than recurrent neural networks (RNNs), which are more flexible and make fewer assumptions about the underlying decision-making processes. Unfortunately, the parameter and latent activity spaces of RNNs are generally high-dimensional and uninterpretable, making it hard to use them to study individual differences. Here, we show how to benefit from the flexibility of RNNs while representing individual differences in a low-dimensional and interpretable space. To achieve this, we propose a novel end-to-end learning framework in which an encoder is trained to map the behavior of subjects into a low-dimensional latent space. These low-dimensional representations are used to generate the parameters of individual RNNs corresponding to the decision-making process of each subject. We introduce terms into the loss function that ensure that the latent dimensions are informative and disentangled, i.e., encouraged to have distinct effects on behavior. This allows them to align with separate facets of individual differences. We illustrate the performance of our framework on synthetic data as well as a dataset including the behavior of patients with psychiatric disorders.

Author Information

Amir Dezfouli (Data61, CSIRO)
Hassan Ashtiani (McMaster University)
Omar Ghattas (University of Chicago)
Richard Nock (Data61, the Australian National University and the University of Sydney)
Peter Dayan (Max Planck Institute for Biological Cybernetics)
Cheng Soon Ong (Data61 and Australian National University)

Cheng Soon Ong is a principal research scientist at the Machine Learning Research Group, Data61, CSIRO, and is the director of the machine learning and artificial intelligence future science platform at CSIRO. He is also an adjunct associate professor at the Australian National University. He is interested in enabling scientific discovery by extending statistical machine learning methods.

More from the Same Authors