Disentangled behavioural representations

Authors: Amir Dezfouli, Hassan Ashtiani, Omar Ghattas, Richard Nock, Peter Dayan, Cheng Soon Ong

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We illustrate the performance of our framework on synthetic data as well as a dataset including the behavior of patients with psychiatric disorders.
Researcher Affiliation Collaboration 1Data61, CSIRO 2Mc Master University 3University of Chicago 4Australian National University 5University of Sydney 6Max Planck Institute
Pseudocode No The paper describes its model and training objective using prose and mathematical formulas, but does not include any explicit pseudocode or algorithm blocks.
Open Source Code No The paper does not contain an explicit statement about releasing source code or a link to a code repository for the described methodology.
Open Datasets Yes BD dataset. This dataset [Dezfouli et al., 2019] comprises behavioural data from 34 patients with depression, 33 with bipolar disorder and 34 matched healthy controls.
Dataset Splits Yes We generated N = 1500 agents (saving 30% for testing). The test data was used for determining the optimal number of training iterations (early stopping). Out of the 12 sequences of each subject, 8 were used for training and 4 for testing to determine the optimal number of training iterations (see Figure S7 for the training curves and Supplementary Material for more details).
Hardware Specification No The paper does not provide specific hardware details such as GPU or CPU models, memory, or cloud computing specifications used for running the experiments.
Software Dependencies No We use the automatic differentiation in Tensorflow [Abadi et al., 2016]. The smoothed black lines were calculated using method gam in R [Wood, 2011]. These mentions do not include specific version numbers for the software.
Experiment Setup No The model parameters Θenc and Θdec were trained based on the above objective function and using gradient descent optimisation method [Kingma and Ba, 2014]. This describes the optimization method but lacks specific hyperparameters like learning rate, batch size, or number of epochs in the main text.